检索结果-内蒙古大学图书馆

Pioneering Developments in computer science & Digital Technologies (IC2SDT), International Conference on

作者： Deepak Upadhyay Mridul Gupta Kunj Bihari Sharma Abhay Upadhyay Dept. of Computer Science and Engineering Graphic Era Hill University Dehradun India Dept. of Electronics and Communication Engineering Graphic Era deemed to be University Dehradun India Dept. of Computer Science and Engineering Graphic Era Deemed to be University Dehradun India

ISBN: (数字)9798350365016

ISBN: (纸本)9798350365023

Throughout this paper, the reader was able to better understand how innovative optimization techniques through NFV and SFC frameworks could and should be applied to address the developing and shifting focus of contemporary network infrastructures. Focusing on performance metrics performance via latency, throughput, resource utilization, and operational cost, the presented algorithms and machine learning models developed and executed due to this research showed innovative and dynamic optimization of network functions. Through further extensive simulations equalling 125 seconds, our findings reported creative results of improving performance in several significant areas: latency was reduced, throughput was enhanced, resource utilization was more efficient, and operational cost was reduced. These results indicated that our optimization strategies can pay off and bring a number of benefits to NFV and SFC that address a clear need for change in the current type of network management models. Therefore, this paper is valuable and serves as a testament of our strategies' power along with opening various doors for following network optimization research. Therefore, one can see how important it is to implement innovation in the face of change.

关键词： Measurement Technological innovation Costs Machine learning algorithms Heuristic algorithms Machine learning Throughput Network function virtualization Resource management Optimization

来源：评论

学校读者我要写书评

暂无评论

Optimization of Building Construction Control System Based on Nonlinear Image Enhancement

引用

computer-Aided Design and Applications 2023年 20卷 213-224页

作者： Liu, Congru Lin, Mingsen Ghafoor, Kayhan Zrar Al-Dabagh, Mustafa Zuhaer Nayef Karras, Dimitrios A. School of Urban Construction Wuhan University of Science and Technology Wuhan China Changjiang Polytechnic Wuhan China Department of Computer Science Knowledge University Erbil44001 Iraq Department of Software & Informatics Engineering Salahaddin University-Erbil Erbil44001 Iraq School of Science Dept. General Athens Greece

To reflect the nonlinear characteristics of the building structural adjustment system, an active vibration control strategy based on the nonlinear is proposed. In this method, the size of the structural control force is determined by comparing the allowable energy with the actual energy, and its direction is determined by taking the derivative of the energy. Because there is no need to solve the linear matrix inequality, the calculation is simple and the operation is convenient. Moreover, when multiple actuators with the same capacity limit are used, the control output force is consistent, thus avoiding the design of multiple control systems and simplifying the controller design. The simulation results show that the maximum controlled displacements of floor 6 to floor 8 are 1.16cm, 1.12cm, and 0.97cm, respectively. The proposed nonlinear energy control method has the advantages of simple control process and avoiding actuator saturation. © 2023 CAD Solutions, LLC.

关键词： Floors

来源：评论

学校读者我要写书评

暂无评论

Privacy-Enhanced Image Restoration in Remote Sensing via Federated Learning

TechRxiv

引用

TechRxiv 2024年

作者： Khan, Muhammad Jahanzeb Rath, Suman Zaib, Muhammad Hassan Dept. of Computer Science and Engineering University of Nevada Reno Reno United States Dept. of Computer Science Air University Islamabad Pakistan

This research addresses the dual challenges of image restoration quality and data privacy in optical remote sensing. Traditional restoration methods often fall short due to the complex nature of remote sensing images, and data privacy concerns further complicate the use of advanced techniques. By integrating the Deep Memory Connected Neural Network (DMCN) with the Data-Decoupled Federated Learning (DDFL) framework, our approach enables significant improvements in image restoration without requiring direct access to sensitive raw data. This method not only enhances data privacy by leveraging federated learning principles but also incorporates advanced techniques like Gaussian image denoising to maintain high restoration quality despite potential noise introduced by the federated process. The performance of the federated DMCN, particularly on the UCMERCED dataset, demonstrates minimal accuracy degradation, even in the presence of noise, while the strategic use of Downsampling Units within DMCN optimizes computational efficiency. Our comprehensive evaluations reveal the effectiveness of this approach in balancing data privacy with the need for high-quality image restoration, suggesting a promising direction for future advancements in remote sensing applications. © 2024, CC BY.

关键词： Optical remote sensing

来源：评论

学校读者我要写书评

暂无评论

An Ensemble Deep Learning Framework for Binary Classification of COVID-19 Cases Using the VGG16 (Visual Geometry Group 16) Architecture: A Comprehensive Analysis and Performance Evaluation

An Ensemble Deep Learning Framework for Binary Classificatio...

引用

Disruptive Technologies (ICDT), International Conference on

作者： Deepak Upadhyay Mridul Gupta Somesh Mishra Saksham Mittal Dept. of Computer Science and Engineering Graphic Era Hill University Dehradun India Dept. of Electronics and Communication Engineering Graphic Era deemed to be University Dehradun India Dept. of Computer Science and Engineering Graphic Era Deemed to be University Dehradun India

This paper presents a novel approach to deep learning by putting forth a cooperative system that uses the VGG16 architecture to categorise COVID-19 examples into two groups. Our model is distinguished by its remarkable recall metrics and precision, which achieve a careful balance that is essential for accurate categorization. What's more impressive is how well the model performs in the non-COVID category, effectively differentiating between COVID and non-COVID cases. With a remarkable overall accuracy of 96%, the model successfully classifies cases from both groups, demonstrating the potential of our suggested framework as a useful diagnostic tool useful in various clinical contexts. This work clarifies the effectiveness of deep learning techniques, concentrating on the VGG16 architecture in the crucial job of binary classification for COVID-19 identification. Our results open up new avenues for investigation in the field of accurate medical diagnosis in addition to providing insights into the real-world applications of sophisticated machine learning. The study highlights the ensemble approach's encouraging benefits, showing how it may strengthen diagnostic precision and advance clinical decision-making.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Approach of Fog Computing and Edge Computing for Computing Resources Optimization Strategies

An Approach of Fog Computing and Edge Computing for Computin...

引用

Pioneering Developments in computer science & Digital Technologies (IC2SDT), International Conference on

作者： Deepak Upadhyay Abhay Upadhyay Mridul Gupta Kunj Bihari Sharma Devansh Yadav Dept. of Computer Science and Engineering Graphic Era Hill University Dehradun India Dept. of Computer Science and Engineering Graphic Era deemed to be University Dehradun India Dept. of Electronics and Communication Engineering Graphic Era deemed to be University Dehradun India

ISBN: (数字)9798350365016

ISBN: (纸本)9798350365023

This paper investigates optimization strategies for fog and edge computing systems, focusing on the key challenges of resource allocation, load balancing, latency minimization, and power efficiency. We analyze the results of the simulation study to determine the impact and potential of our strategies and find that the improvements achieved are small to moderate, varying between 1.75% and 2.95%. This knowledge demonstrates that system optimization requires small, gradual increments and that fog and edge computing are dynamic systems. Our results suggest that optimization based on integration and adaptability can produce a significant difference in the performance and reliability of distributed systems.

关键词： System performance Focusing Minimization Load management Reliability Resource management Dynamical systems Distributed computing Optimization Edge computing

来源：评论

学校读者我要写书评

暂无评论

Efficient Energy Management Algorithm for Single Stage SPV Based Water Pumping System Without Batteries

Efficient Energy Management Algorithm for Single Stage SPV B...

引用

2024 International Conference on Sustainable Power and Energy, ICSPE 2024

作者： Krishna, T. Murali Trrad, Issam Harish, Cholleti Nimer, Hamsa Al-Mattarneh, Hashem Monisha Jothi, R. Ravindra, J.V.R. Chaitanya Bharati Institute of Technology Department of EEE Telangana Hyderabad India Jadara University Department of Computer and Communication Engineering Irbid Jordan Yarmouk University Department of Civil Engineering Irbid Jordan New Prince Shri Bhavani College of Engineering and Technology Dept. of CSE Tamil Nadu Chennai India Vardhaman College of Engineering Department of ECE Telangana Hyderabad India

ISBN: (纸本)9798350366051

Solar Photovoltaic (SPV) based standalone water pumping systems especially without batteries are becoming more popular due to its feature. The SPV system output power is always varying and depends on solar irradiance which cannot be regulated and unpredictable. Hence, standalone water pumping system without integrating any storage device is a challenging task. Further, an appropriate control method must be required to regulate speed of the motor according to power available from SPV system. In this paper an induction motor is considered and developed a novel energy management algorithm to operate battery less standalone water pumping system powered by SPV system. To obtain higher efficiency and utilization, maximum power point tracking (MPPT) device is also developed. A single stage water pumping system is developed by integrating control of inverter to MPPT algorithm. The dc-link voltage is also regulated along with speed of the induction motor by proposed control methodology. A multi motor-pump sets are considered for the application of agriculture. In order to get an effective operation, deloading concept is also included in the proposed control method. Various results are demonstrated by performing OPAL-RT modules based hardware-in the-loop. © 2024 IEEE.

关键词： Solar concentrators

来源：评论

学校读者我要写书评

暂无评论

Predicting Customer Purchase Intent Using Logistic Regression: A Data-Driven Approach 2

Predicting Customer Purchase Intent Using Logistic Regressio...

引用

2nd International Conference on Machine Learning and Autonomous Systems, ICMLAS 2025

作者： Rajarajachozhan, C. Karthika, G. Rajakrishnammal, A. Mano, M. Kumar, P. Nithish Jayahari, E. Saveetha Engineering College Dept. of Electronics and Communication Engineering Tamil Nadu Chennai India Saveetha Engineering College Dept. of Artificial Intelligence and Data Science Tamil Nadu Chennai India Saveetha Engineering College Dept. of Computer Science and Engineering Tamil Nadu Chennai India

ISBN: (纸本)9798331505745

Predicting customer purchase intent is crucial for modern businesses in order to improve engagement, refine marketing strategies, and increase revenue. Conventional rule-based systems encounter difficulties with dynamic and extensive customer data, limiting their flexibility and precision. This project employs a machine learning methodology utilizing logistic regression to forecast customer intent based on demographic, transactional, and behavioral data. The proposed model analyses input features including age, browsing history, and previous purchases, employing sophisticated data preprocessing methods such as One-Hot Encoding and feature scaling to guarantee data integrity. Through hyperparameter tuning and the assessment of critical metrics including accuracy, precision, recall, and Fl-score, the system provides dependable and actionable insights. Real-time predictive capabilities enable businesses to customize customer interactions, facilitating targeted marketing and enhancing customer experience. This project underscores the capacity of predictive analytics to tackle real-world issues, facilitating data-driven decision-making and sustainable business development. © 2025 IEEE.

关键词： Logistic regression

来源：评论

学校读者我要写书评

暂无评论

Pruning Binarized Neural Networks Enables Low-Latency, Low-Power FPGA-Based Handwritten Digit Classification

Pruning Binarized Neural Networks Enables Low-Latency, Low-P...

引用

IEEE Conference on High Performance Extreme Computing (HPEC)

作者： Syamantak Payra Gabriel Loke Yoel Fink Joseph D. Steinmeyer Dept. of Electrical Engineering Stanford University (formerly Dept. of Electrical Engineering and Computer Science Massachusetts Institute of Technology) Dept. of Materials Science and Engineering Massachusetts Institute of Technology Dept. of Materials Science and Engineering Dept. of Electrical Engineering and Computer Science and Institute for Soldier Nanotechnologies Massachusetts Institute of Technology Dept. of Electrical Enigneering and Computer Science Massachusetts Institute of Technology

As neural networks are increasingly deployed on mobile and distributed computing platforms, there is a need to lower latency and increase computational speed while decreasing power and memory usage. Rather than using FPGAs as accelerators in tandem with CPUs or GPUs, we directly encode individual neural network layers as combinational logic within FPGA hardware. Utilizing binarized neural networks minimizes the arithmetic computation required, shrinking latency to only the signal propagation delay. We evaluate size-optimization strategies and demonstrate network compression via weight quantization and weight-model unification, achieving 96% of the accuracy of baseline MNIST digit classification models while using only 3% of the memory. We further achieve 86% decrease in model footprint, 8mW dynamic power consumption, and $< 9\text{ns}$ latency, validating the versatility and capability of feature-strength-based pruning approaches for binarized neural networks to flexibly meet performance requirements amid application resource constraints.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Channel Capacity Enhancement in Dual Branch MRC under Extreme Fading Using Quantum Computing

Channel Capacity Enhancement in Dual Branch MRC under Extrem...

引用

IEEE Region 10 Symposium

作者： Deepak Upadhyay Kunj Bihari Sharma Mridul Gupta Abhay Upadhyay Dept. of Computer Science and Engineering Graphic Era Hill University Dehradun India Dept. of Computer Science and Engineering Graphic Era deemed to be University Dehradun India Dept. of Electronics and Communication Engineering Graphic Era deemed to be University Dehradun India

ISBN: (数字)9798350364866

ISBN: (纸本)9798350364873

We have investigated the potential of channel capacity and signal integrity enhancement in dual branch MRC systems even under extreme fading through classical and quantum computing. We have used the classical algorithm to gauge the performance of the quantum algorithm, including QAOA and QEC. Our simulation results show that quantum-assisted MRC work optimally by providing superior SNR and BER. Quantum algorithms not only maximizes the effective channel capacity but also minimizes end-to-end system latency and number of error rate more efficiently. The addition of Quantum Machine Learning for the dynamic parameter setting in real-time has demonstrated that it may be possible to combat severe fading effects. To the best of our knowledge, this paper laid the cornerstone to explore more opportunities in implementing quantum-enabled techniques for advanced telecommunication system development to realize more robust and efficient technologies.

关键词： Fading channels Technological innovation Quantum algorithm Channel capacity Simulation Machine learning Real-time systems Telecommunications Signal integrity Signal to noise ratio

来源：评论

学校读者我要写书评

暂无评论

Copy-Move Forgery Detection in Digital Forensic Images Using CNN 7

Copy-Move Forgery Detection in Digital Forensic Images Using...

引用

7th International Conference on computer science and engineering, UBMK 2022

作者： Kaya, Mustafa Sani, Khalid Jibril Karakus, Serkan Firat University Dept. of Digital Forensics Engineering Elazig Turkey Federal University of Kashere Dept. of Computer Science Gombe Nigeria

ISBN: (数字)9781665470100

ISBN: (纸本)9781665470100

Digital images are commonly used for sharing visual information and can be manipulated easily. The detection forgery in digital images has become a hot domain of research in digital image forensics due to the prevalent use of image editing tools for manipulating an image to conceal or distort information in the image. One of the most common image forgeries performed is the copy-move forgery. This type of forgery involves copying a segment of the image, which is then pasted to a different segment of the same image. The need for detecting whether an image is authentic becomes essential. The existing methods implemented for detecting image forgeries were based on traditional feature extraction algorithms such as block-based and key point-based algorithms. These traditional techniques employed produce a low-performance result. Deep learning techniques have proven to provide better performance in image processing tasks. In this research, a convolutional neural network based on a pre-trained ResNet50 network was proposed to detect copy-move forgeries in digital images. The proposed model uses the CoMoFoD image dataset in experimenting. The metric evaluation results achieved in the proposed model show that deep learning methods performance is more effective in digital image copy-move forgery detection. © 2022 IEEE.

关键词： Digital forensics

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：