检索结果-内蒙古大学图书馆

IEEE International Conference on Systems, Man and Cybernetics

作者： Haitao Yuan Qinglong Hu Jing Bi Wei Zhang Jia Zhang MengChu Zhou School of Automation Science and Electrical Engineering Beihang University Beijing China Dept. of Computer Science City University of Hong Kong Hong Kong China College of Computer Beijing University of Technology Beijing China Dept. of Computer Science and Engineering University of Connecticut Storrs CT USA Dept. of Computer Science Southern Methodist University Dallas TX USA Dept. of Electrical and Computer Engineering New Jersey Institute of Technology Newark NJ USA

ISBN: (数字)9781665410205

ISBN: (纸本)9781665410212

In recent years, distributed computing has wit-nessed widespread applications across numerous organizations. Predicting workload and computing resource data can facilitate proactive service operation management, leading to substantial improvements in quality of service and cost efficiency. However, these data often exhibit non-linearity, high volatility, and inter-dependencies across different categories, presenting challenges for accurate forecasting. Consequently, there is a critical need to develop a method that thoroughly and comprehensively analyzes all available data to forecast future trends effectively. This work proposes a novel integrated data-enhanced prediction model named SVI for achieving high-accuracy workload prediction in distributed computing systems. SVI employs the Savitzky-Golay filter and variational mode decomposition for feature processing, whose features are subsequently utilized by Informer for multivariate joint analysis of the enhanced data, achieving high-precision prediction. Ablation and comparative experiments with advanced prediction models are conducted on the Google cluster trace and other typical datasets. Realistic data-driven results indicate that SVI improves the prediction accuracy by 35.4% compared to the original Informer, with each module contributing to the performance enhancement. Furthermore, compared with Autoformer, SVI enhances the prediction accuracy of workload, CPU, and memory by 62.5%, 65.6%, and 69.1 %, respectively.

关键词： Training Accuracy Costs Computational modeling Memory management Organizations Quality of service Predictive models Market research Internet

来源：评论

学校读者我要写书评

暂无评论

Secure and Traceable QR Code Using Blockchain-enabled Certificates 11

Secure and Traceable QR Code Using Blockchain-enabled Certif...

引用

11th IEEE International Conference on Communication Systems and Network Technologies, CSNT 2022

作者： Bhadoria, Robin Singh Goyal, Akshat Das, Arka Prabha Bashar, Abul Zikria, Mohammed Gla University Dept. of Computer Engineering and Applications Mathura India Dept. of Cse Mathura India Bhopal India Prince Mohammad Bin Fahd University College of Computer Engineering and Science Khobar Saudi Arabia

ISBN: (纸本)9781665480383

The blockchain has been considered to be a breakthrough technology solution for problems based on security aspects. It is a Distributed Ledger Technology (DLT) which can be used to established trust among different trustless entities or nodes present in the network. Furthermore, Quick Response (QR) Codes are likewise one of the most promising innovations going on in the markets. In QR code, small dots are present which get converted to binary numbers and get validated with error correcting algorithms. Hence, QR codes are beneficial for both storage and authentication. In this article, we discuss the prospects of combination of these two technologies for better results. In this paper, we aim to develop permission-less Blockchain, which is relatively easier to compute and have shown to increase its data capacity. It also endeavored to add the QR Code incorporation to a block and make it more scalable with considering the limited space in a such block. © 2022 IEEE.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

High-Performance Face Identification Using Randomly Selected Channels from Hyperspectral Images

High-Performance Face Identification Using Randomly Selected...

引用

IEEE International Workshop on Imaging Systems and Techniques (IST)

作者： Sota Furusawa Chinthaka Premachandra Dept. of Electrical Engineering and Computer Science Graduate School of Engineering and Science Shibaura Institute of Technology Tokyo Japan

ISBN: (数字)9798350378214

ISBN: (纸本)9798350378221

With the recent development of information technology, the importance of protecting personal information has increased. Because of the vulnerability in passwords, biometric authentication is now being used as a method of personal information protection. However, biometric authentication has the possibility of malicious authentication due to the emergence of technology that can generate biometric data that is difficult to duplicate. Therefore, this study aimed to solve the security problems posed by Generative Adversarial Networks (GANs) in biometric authentication by using Hyperspectral Images (HSI). We searched for solutions to the problems identified in previous studies, such as the inability to correctly identify individuals who have not been previously learned and the length of time required for identification. In this paper, we used three channels of data randomly selected from hyperspectral face images for learning to identify individuals by binary classification into “learned subject (class)” and “unlearned subjects (classes)”. In this case, discriminators based on the least-squares generative adversarial network (LSGAN) model was developed for each class using three randomly selected channels of data from the HSI for two class classification. The proposed method significantly reduced the identification time and achieved very high discrimination accuracy in all classes. In addition, the results showed high accuracy throughout multiple face identification experiments.

关键词： Accuracy Passwords Biometric authentication Generative adversarial networks Search problems Security Protection Information technology Faces Hyperspectral imaging

来源：评论

学校读者我要写书评

暂无评论

Human Activity Recognition using Smartphone Dataset: A Review

Human Activity Recognition using Smartphone Dataset: A Revie...

引用

2022 International Conference on Edge Computing and Applications, ICECAA 2022

作者： Verma, Apurv Verma, Vijayant Patel, Brijesh Dept. of Computer Science and Engineering School of Engineering and I.T. MATS University Raipur India Dept. of Mechanical Engineering School of Engineering and I.T. MATS University Raipur India

ISBN: (数字)9781665482325

ISBN: (纸本)9781665482325

Cell Phones are becoming more refined with each new model release. These days phones ordinarily consolidate numerous sensors for various functions such as GPS tracking, temperature sensors, accelerometer, gyroscope, high-determination cameras. In recent years, Human Activity Recognition (HAR) has enabled various applications. The information gathered by HAR may be utilized for a number of reasons, including fitness tracking, health and safety, and entertainment, among others. An abundance of research has been conducted on real-time processing, which has resulted in increased power consumption of mobile devices. It is preferable that the activity identification process be as precise as possible, because of the resource limited feature of a mobile device. So, the research is to use the dataset from the smartphone and use various classification models to find out which classifieris more accurate and provides fasterresults. © 2022 IEEE.

关键词： Smartphones

来源：评论

学校读者我要写书评

暂无评论

Analysis of Common Mode Currents and Harmonic Pollution at Supplying Induction Motors from Static Converters with Variable Modulation Frequency

Analysis of Common Mode Currents and Harmonic Pollution at S...

引用

2023 Power Quality and Electromagnetic Compatibility at Low-Frequency, PQEMC-LF 2023

作者： Nuca, Iurie Wan, Lu Nicolae, Petre - Marian Nicolae, Ileana - Diana Grassi, Flavia Wu, Xinglong University of Craiova Electrical Engineering Energetic and Aeronautics Dept. Craiova Romania Politecnico di Milano Department of Electronics Information and Bioengineering Milan Italy University of Craiova Computer Science and Information Technology Dept. Craiova Romania

ISBN: (纸本)9798350341331

The problems of Electromagnetic Compatibility (EMC) in three-phase systems are less studied than single-phase or direct current, due to the smaller ratio of emissions relative to the rated power of such systems. This paper is focused on the problem of emissions in three-phase variable frequency drive systems in the low-frequency EMC range, specifically on the common mode current through the connected ground wire between the static converter and power grid. The common mode current is determined to be variable depending on switching frequency. For a deeper understanding Fast Fourier Transform was used to decompose the signal. Main parameter to understand the magnitude of common mode current was the RMS of the current. The decomposition showed a significant DC component which cannot be picked up by the used RF probe, thus presenting a noise offset necessary to be considered when calculating the total effective value of common mode current. The analysis was made on the time-domain representation and the frequency behavior of the converter. The paper suggests that the standard measurement in the low-frequency range and the picked-up signal are investigated enough, as there is a disparity in the impact of emissions in the low-frequency range compared to what off-the-shelf devices have to offer, which are standard compliant, but still present considerable emissions. © 2023 IEEE.

关键词： Static converters

来源：评论

学校读者我要写书评

暂无评论

An Efficient Salt and Pepper Noise Reduction Approach for Video(s) Using Optimized Filter Approach 2

An Efficient Salt and Pepper Noise Reduction Approach for Vi...

引用

2nd International Conference on Emerging Frontiers in Electrical and Electronic Technologies, ICEFEET 2022

作者： Kumain, Sandeep Chand Singh, Maheep Govil, Mahesh Chandra Pilli, Emmanuel Shubhakar Srinagar India Malaviya National Institute of Technology Jaipur Dept. of Computer Science and Engineering Jaipur India

ISBN: (数字)9781665488754

ISBN: (纸本)9781665488754

In today's digital world, most information is shared through images or videos. Images and videos are more infor-mative than textual data. During the image or video capturing process, addition of noise is one of the major problems. The presence of noise in captured data causes results to be misleading, particularly in computer vision and image processing tasks. As a result, preprocessing is required before tackling tasks like edge detection, object detection, object recognition, salient object detection, video summarization, and so on. Gaussian, Salt & Pepper, Poison, and Speckle noise are the most common types of noise which can affect the video. In this article, the author(s) presented an efficient noise reduction approach for reducing the salt and pepper noise present in the image or video. The performance of the proposed approach is compared with traditional and widely used filters for noise reduction, such as mean, mode, and median. The experimental analysis of the proposed approach is done on the dataset where the videos are captured using the camera as well as from the other resources such as Internet. Noisy videos are prepared by mixing the Salt & Pepper noise with different noise densities (levels) in the video dataset. The experimental results show that the proposed approach outperforms the traditional approaches not only in terms of noise reduction but also in preserving the details in the video. © 2022 IEEE.

关键词： Salt and pepper noise

来源：评论

学校读者我要写书评

暂无评论

Integrating Random Forest and Support Vector Regression Models for Optimized Energy Consumption Evaluation in Cloud Computing Data Centers 3

Integrating Random Forest and Support Vector Regression Mode...

引用

3rd International Conference on Technological Advancements in Computational sciences, ICTACS 2023

作者： Shaik, Nazeer Kumar, B. Vinoth Bhati, Anita Kumar, Sandeep Singh, Jagendra Sahu, Dinesh Prasad SRIT-Autonomous Department of Computer Science Engineering Anantapur India Ksr Institute for Engineering and Technology Dept. of Electronics and Communication Engineering Tiruchengode India Jecrc University Department of Computer Applications Jaipur India Raj Kumar Goel Institute of Technology Department of Information Technology Ghaziabad India School of Computer Science Engineering and Technology Bennett University Greater Noida India

ISBN: (纸本)9798350342338

This study proposes a novel approach for energy consumption evaluation in cloud computing data centers. The immense energy consumption of these data centers presents significant environmental and economic challenges. Traditional evaluation methods often fail to provide accurate estimations due to the complex dynamics of cloud computing environments. The research introduces an integrated model, combining Random Forest Regression and Support Vector Regression, along with a Gradient Boosting Regressor for iterative training of regression parameters. We measure the model's performance using Root Mean Square Error (RMSE) and Mean Absolute Percentage Error (MAPE), replacing traditional relative deviation measures. The proposed approach aims to provide more accurate and efficient energy consumption evaluations, offering potential benefits in energy management, operational costs reduction, and minimizing environmental impact. © 2023 IEEE.

关键词： Cloud Computing Energy Consumption Evaluation Gradient Boosting Regressor Random Forest Regression Support Vector Regression

来源：评论

学校读者我要写书评

暂无评论

Predicting Lifespan of Ground-to-Air Multipath Components in mmWave UAV Channels

arXiv

引用

arXiv 2025年

作者： Khawaja, Wahab Jacobsen, Rune H. Hussain, Sajid Guvenc, Ismail Dept. Electrical and Computer Engineering Aarhus University Aarhus8000 Denmark Dept. Computer Systems Engineering Mirpur Univ. Science and Technology AJK Mirpur10250 Pakistan

In mobile ground-to-air (GA) propagation channels, the birth and death of multipath components (MPCs) are frequently observed, and the wide-sense stationary uncorrelated scattering (WSSUS) assumption does not always hold. Several methods exist for tracking the birth and death of MPCs, however, to the best of knowledge of authors, there is no existing literature that addresses the prediction of the lifespan of the MPCs in non-WSSUS GA propagation channels. In this work, we consider the GA channel as non-WSSUS and individual MPCs across receiver positions are represented as time series based on the Euclidean distance between channel parameters of the MPCs. These time series representations, referred to as path bins, are analyzed using a semi-Markov chain model. The channel parameter variations and dependencies between path bins are used to predict the lifespan of path bins using weighted sum method, machine learning classifiers, and deep neural networks. For comparison, the birth and death of path bins are also modeled using a Poisson distribution and a Markov chain. Simulation results demonstrate that deep neural networks offer highly accurate predictions for the lifespan (including death) of MPC path bins in the considered GA propagation scenario. © 2025, CC BY.

关键词： Markov chains

来源：评论

学校读者我要写书评

暂无评论

Machine Learning-based sEMG Signal Classification for Hand Gesture Recognition

Machine Learning-based sEMG Signal Classification for Hand G...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Parshuram N. Aarotale Ajita Rattani Dept. of Biomedical Engineering Wichita State University USA Dept. of Computer Science and Engineering Uni. of North Texas USA

ISBN: (数字)9798350386226

ISBN: (纸本)9798350386233

EMG-based hand gesture recognition uses electromyographic (EMG) signals to interpret and classify hand movements by analyzing electrical activity generated by muscle contractions. It has wide applications in prosthesis control, rehabilitation training, and human-computer interaction. Using electrodes placed on the skin, the EMG sensor captures muscle signals, which are processed and filtered to reduce noise. Numerous feature extraction and machine learning algorithms have been proposed to extract and classify muscle signals to distinguish between various hand *** paper aims to benchmark the performance of EMG-based hand gesture recognition using novel feature extraction methods, namely, fused time-domain descriptors, temporal-spatial descriptors, and wavelet transform-based features, combined with the state-of-the-art machine and deep learning models. Experimental investigations on the Grabmyo dataset demonstrate that the 1D Dilated CNN performed the best with an accuracy of 97% using fused time-domain descriptors such as power spectral moments, sparsity, irregularity factor and waveform length ratio. Similarly, on the FORS-EMG dataset, random forest performed the best with an accuracy of 94.95% using temporal-spatial descriptors (which include time domain features along with additional features such as coefficient of variation (COV), and Teager-Kaiser energy operator (TKEO)).

关键词： Hands Deep learning Wavelet transforms Accuracy Biological system modeling Gesture recognition Muscles Feature extraction Electromyography Time-domain analysis

来源：评论

学校读者我要写书评

暂无评论

Intervention Analysis for Predicting Stock Market using Deep Learning Algorithms and Time Series Analysis

Intervention Analysis for Predicting Stock Market using Deep...

引用

International Conference on Computing and Networking Technology (ICCNT)

作者： Krish Valecha Yash Pandloskar Sowmya Dadheech Pradnya Saval Dept. of Computer Science and Engineering (Data Science) Dwarkadas J. Sanghvi College of Engineering Mumbai India

ISBN: (数字)9798350370249

ISBN: (纸本)9798350370270

Stock market being intricate and volatile pose challenges for classical Time Series Analysis techniques in terms of generalization and computation on real-world data. In order to improve prediction capacities, new methods like intervention analysis and Deep Learning (DL) are required. The research seeks to unravel the complexities of stock price prediction modelling by comparing Time Series Analysis with Deep Learning augmented by intervention analysis. Upon evaluation on different datasets, the Deep Learning models, specifically the Recurrent Neural Network (RNN) performed better than the other models considered. RNN outperformed other models on Mean Squared Error (MSE) for Tesla and IBM data, with values 3.874 before intervention and 3.593 after intervention and 46.52 before intervention and 42.97 after intervention respectively, thus highlighting the advantages of Deep Learning models for predictions. The goal of investigating intervention analysis methods incorporated into predictive models is to create processes that can predict overall market trends and efficiently identify and address sudden deviations.

关键词： Deep learning Analytical models Recurrent neural networks Accuracy Computational modeling Time series analysis Predictive models Market research Data models Stock markets

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：