检索结果-内蒙古大学图书馆

IEEE Networking Letters 2022年第3期4卷 127-131页

作者： Kumar, Vikas Mukherjee, Mithun Lloret, Jaime Zhang, Qi Kumari, Mamta Bharat Sanchar Nigam Ltd. Network and Co-ordination Section Patna800001 India Nanjing University of Information Science and Technology School of Artificial Intelligence Nanjing210044 China Instituto de Investigacion Para la Gestion Integrada de Zonas Costears Universitat Politecnica de Valencia Valencia46022 Spain Aarhus University Department of Electrical and Computer Engineering Digit Aarhus8000 Denmark Ramchandra Chandravansi Institute of Technology Department of Computer Science and Engineering Bishrampur822124 India

To take the advantage of computing resource of edge server, the end-users must pay the service charge for task processing. However, the transmission delay plays an important role in communication-computation of edge computing. To address this, we aim to leverage reconfigurable intelligent surface (RIS) in mobile edge computing (MEC). In this letter, we propose an offloading policy to maximize the revenue of edge server while satisfying the end-user's goal of minimizing both the latency and cost based on the price by edge server. We provide an insight on required computing resources at the edge server for delay-sensitive task processing. © 2019 IEEE.

关键词： computation offloading

来源：评论

学校读者我要写书评

暂无评论

An integrated fuzzy adjusted cosine similarity and TOPSIS based recommendation system for information system requirements selection

引用

Decision Analytics Journal 2024年 11卷

作者： Akram, Faiz Ahmad, Tanvir Sadiq, Mohd. Department of Computer Engineering Faculty of Engineering and Technology Jamia Millia Islamia A Central University New Delhi 110025 India Software Engineering Laboratory Computer Engineering Section UPFET Jamia Millia Islamia A Central University New Delhi 110025 India

Selecting the requirements for an information system based on their ranking values is one of the critical steps in software development. Various methods for computing the ranking order of the requirements have been developed using multi-criteria decision-making methods. This study shows selecting the requirements for different software releases using a recommendation system is an unresearched problem. We present a recommendation system (PRecSys) for computing the ranking order of the requirements in an information system using fuzzy-based adjusted cosine similarity measure and collaborative filtering to recommend the requirements to stakeholders with similar interests. The ranking order of the information systems requirements in PRecSys is computed using the fuzzy Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS). The applicability of PRecSys is discussed by considering the requirements for a library information system. The PRecSys is compared with PHandler, an expert system for choosing the requirements, based on the following criteria: agreement measure, the number of judgments by decision-makers, and time complexity. © 2024 The Authors

关键词： Collaborative filtering Fuzzy TOPSIS Library information system Multi-criteria decision making Recommendation system Requirements elicitation

来源：评论

学校读者我要写书评

暂无评论

Human movement science-informed multi-task spatio temporal graph convolutional networks for fitness action recognition and evaluation

引用

Applied Soft Computing 2024年 164卷

作者： Chang, Jia-Wei Chen, Ming-Hung Ma, Hao-Shang Liu, Hao-Lan Department of Computer Science and Information Engineering National Taichung University of Science and Technology No. 129 Section 3 Sanmin Road North District Taichung City404 Taiwan Physical Education Section National Taichung University of Science and Technology No. 129 Section 3 Sanmin Road North District Taichung City404 Taiwan

In recent years, with the rise of health consciousness, people's demand for fitness has steadily increased. Utilizing automated human action recognition technology to monitor users’ movements during exercise continuously would help prevent situations where incorrect movements lead to injuries while working out. Skeleton-based human action recognition methods can overcome the susceptibility of past color-based and depth-based methods to various external backgrounds and noise, becoming a more successful solution in recent years. In this study, the auto-fitness advisor system we propose not only identifies the category of the action but also assesses the quality of the action and provides suggestions. We integrate human movement science, such as the Five Primary Kinetic Chains (5PKC), which defines the primary physiological principles in human movement, to enhance the accuracy of fitness action recognition by providing a more precise relationship between the human skeleton and muscles. For assessing the quality of movements and providing suggestions, we have designed a multi-task objective function within our model. Overall, the proposed model is a multi-task model based on Spatio Temporal Graph Convolutional Networks (ST-GCN), which employs the Five Primary Kinetic Chains (5PKC) as a partitioning strategy for skeletal information. In our experiments, we not only collected a certain amount of datasets in gyms to validate the performance of our model but also compared it with other current methods using existing public datasets. © 2024 Elsevier B.V.

关键词： Kinetics

来源：评论

学校读者我要写书评

暂无评论

A gazelle optimization expedition for key term separated fractional nonlinear systems with application to electrically stimulated muscle modeling

引用

Chaos, Solitons and Fractals 2024年 185卷

作者： Khan, Taimoor Ali Chaudhary, Naveed Ishtiaq Hsu, Chung-Chian Mehmood, Khizer Khan, Zeshan Aslam Raja, Muhammad Asif Zahoor Shu, Chi-Min International Graduate School of Artificial Intelligence National Yunlin University of Science and Technology 123 University Road Section 3 Douliou Yunlin64002 Taiwan Future Technology Research Center National Yunlin University of Science and Technology 123 University Road Section 3 Douliou Yunlin64002 Taiwan Department of Information Management National Yunlin University of Science and Technology 123 University Road Section 3 Douliou Yunlin64002 Taiwan Department of Electrical and Computer Engineering International Islamic University Islamabad Pakistan Department of Safety Health and Environmental Engineering National Yunlin University of Science and Technology 123 University Road Section 3 Douliou Yunlin64002 Taiwan

Various real-time processes are effectively represented with a fractional nonlinear autoregressive exogenous (F-NARX) model where estimation of model parameters is considered as an essential task. In this study, a population-based gazelle optimization algorithm (GOA) inspired by the evolutionary characteristics of gazelle's is exploited for the parameter estimation of the key term-separated F-NARX system. The Grünwald-Letnikov derivative, a fractional order calculus operator is integrated to develop the F-NARX system from a conventional non-linear autoregressive system. The mean square error-based merit function is developed and the effectiveness of the GOA for the F-NARX system is analyzed in terms of speedy convergence, estimation accuracy, complexity and robustness for different noise scenarios. The extendibility of the GOA is assessed through the estimation of stiff parameters of the electrically stimulated muscle model (ESMM) required for rehabilitation of paralyzed muscles. The efficacy of the GOA is endorsed through Wilcoxon signed rank statistical test in comparison with recent counterparts of Runge Kutta optimization algorithm, Whale optimization algorithm, and Harris Hawks optimization algorithm. © 2024 Elsevier Ltd

关键词： Parameter estimation

来源：评论

学校读者我要写书评

暂无评论

Data-Driven Power Flow Estimation for MVDC Distribution Systems Based on Physics-Embedded FCN

引用

IEEE Transactions on Smart Grid 2025年

作者： Sun, Pingyang Wu, Rongcheng Shen, Zhiwei Wang, Hongyi Li, Gen Khalid, Muhammad Konstantinou, Georgios School of Electrical Engineering and Telecommunications UNSW Sydney Australia University of Technology Sydney Data Science Institute Australia Aalborg University Department of AAU energy Denmark Energy Technology and Computer Science Section Department of Engineering Technology Ballerup2750 Denmark King Fahd University of Petroleum and Minerals Electrical Engineering Department Interdisciplinary Research Center for Sustainable Energy Systems Dhahran31261 Saudi Arabia

Maintaining high prediction accuracy with varying grid topologies poses a significant challenge to adopting neural network (NN)-based approaches for power flow (PF) estimation in medium-voltage direct current (MVDC) distribution systems. This paper proposes a physics-embedded fully convolutional network (PEFCN) to improve the accuracy. Physics-embedded techniques are incorporated in the proposed PEFCN through 1) architecture reconstruction, and 2) loss function reformulation. Architecture is reconstructed by input channel conversion calculation in a new physics operation layer. This process offers physical connections among the three input matrix channels (voltage, current, and line conductance). Three new physics loss terms are included in the loss function to restrict the outliers violating the limits of converter power ratings and terminal MVDC voltages. The two operations enable the FCN to achieve improved prediction accuracy and strong generalization capabilities. Five MVDC distribution systems, characterized by different dc voltage levels and topology configurations, serve to validate the superiority of the proposed PEFCN over other NNs in the PF estimation for scenarios involving both fixed and varying system structures. Moreover, a modified IEEE 69-bus distribution system is further used to demonstrate the applicability of the proposed PEFCN for larger systems. © 2010-2012 IEEE.

关键词： DC distribution systems

来源：评论

学校读者我要写书评

暂无评论

Hybrid Full-Bridge Phase-Shift and Half-Bridge LLC Resonant Converter Based on Dual Transformers 10

Hybrid Full-Bridge Phase-Shift and Half-Bridge LLC Resonant ...

引用

10th International Conference on Applied System Innovation, ICASI 2024

作者： Hua, Chih-Chiang Chuang, Ching-Chun Hong, Min-Rui Wang, Jian-Min National Yunlin University of Science and Technology Department of Electrical Engineering 123 University Road Section 3 Yunlin Douliou64002 Taiwan National Kaohaiung University of Science and Technology Department of Electrical Engineering No. 415 Jiangong Rd. Sanmin Dist Kaohsiung City807618 Taiwan National Formosa University Computer Science and Information Engineering No.64 Wunhua Rd. Huwei Township Yunlin County632 Taiwan Graduate Institute of Vehicle Engineering National Formosa University No.64 Wunhua Rd. Huwei Township Yunlin County632 Taiwan

ISBN: (纸本)9798350394924

This paper proposes a hybrid full-bridge phase-shift and half-bridge LLC resonant converter based on dual transformers with different output voltages. In the proposed LLC resonant circuit, the power switches can achieve zero-voltage switching, which reduces power losses caused by traditional hard switching. Additionally, the converter continuously operates at the resonant frequency, enabling zero-current switching for the rectifier diodes and enhancing overall converter efficiency. The prototype circuit operates at an input voltage of 400V and fixed frequency with a constant duty ratio. By adjusting the phase shift between PWM square waves to change the output power, the proposed converter achieves a wide range of output voltages from 250V to 450V and a rated capacity of 1kW. The experimental results show that the proposed converter achieves a maximum conversion efficiency of 92.01% at an output voltage of 250V and a maximum conversion efficiency of 93.78% at an output voltage of 450V. © 2024 IEEE.

关键词： Zero voltage switching

来源：评论

学校读者我要写书评

暂无评论

Characterization of plain and ZnO coated D-shaped plastic optical fiber sensor of different diameters 8

Characterization of plain and ZnO coated D-shaped plastic op...

引用

8th International Conference on engineering and Emerging Technologies, ICEET 2022

作者： Khan, Abdul Ali Thirunavakkarasu, Punithavathi M. Saidin, Norazlina Bte Khalaf, Ahmed Lateef Roslan, F.S. Haider, Muhammad Luqman Universiti Kuala Lumpur British Malaysian Institute Communication Technology Section Kuala lumpur53100 Malaysia International Islamic University Malaysia Department of Electrical and Computer Engineering Kuala Lumpur53100 Malaysia Al-ma'Moon University College Department of Computer Engineering Techniques Baghdad Iraq University of Texas at Dallas Department of Electrical Engineering TX United States

ISBN: (纸本)9781665491068

The sensitivity and simple fabrication of fiber sensor are major concerns now a days. In this work, the effect of sensor diameter and zinc oxide (ZnO) sensing layer on the intensity of D-shaped multimode plastic optical fiber (POF) sensor was experimentally investigated. A simple side polishing method was used to prepare a fiber sensor of various diameters having a length of 30 cm. The sensor is coated with ZnO using hydrothermal method. The behavior of both plain and coated fiber sensor in terms of intensity were recorded using spectrometer. After analysis, it was observed that plain and coated sensor having a diameter of 500 generated strong evanescent waves, which resulted in a lower intensity and higher absorbance. The proposed method is efficacious for improving the sensitivity of optical fiber sensors. © 2022 IEEE.

关键词： Zinc oxide

来源：评论

学校读者我要写书评

暂无评论

Intelligent Cancer Detection System

Intelligent Cancer Detection System

引用

2021 International Conference on Intelligent Technologies, CONIT 2021

作者： Das, Utpol Kanti Sikder, Juel Salma, Umme Anwar, A M Shahed Rangamati Science and Technology University Dept. of Computer Science and Engineering Rangamati Bangladesh Bangladesh University Dept. of Computer Science and Engineering Dhaka Bangladesh Rangamati Science and Technology University Dept. of IT Section Rangamati Bangladesh

ISBN: (纸本)9781728185835

Histopathology and MRI produce different types of images and a single procedure to detect cancerous cells from both of them is considered tedious and time-consuming. Therefore, this study proposes a strategy that can perform segmentation, classification and detection over numerous categories of cancer cells. This experimentation demands the preprocessing to intensify the cells' pictorial characteristic and to segment the intended cancerous cell k-means algorithm applied. The Convolutional Neural Network (CNN) classifier being considered as the best method classifying the test image using the feature extraction method on the filtered cell. Considering the system detects cancer, different morphological operations are applied on the extracted cancer region, and finally, we calculated the percentage of the cancerous area. The MATLAB environment has been used on Histopathology and MRI images of the infected cell from various authentic datasets of various cancers mainly Brain, Breast, Leukemia and Lung cancer. The proposed arrangements of methods give improved accuracy as compared to the other existing methods. © 2021 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Design of Runge-Kutta optimization for fractional input nonlinear autoregressive exogenous system identification with key-term separation

引用

Chaos, Solitons and Fractals 2024年 182卷

作者： Khan, Taimoor Ali Chaudhary, Naveed Ishtiaq Khan, Zeshan Aslam Mehmood, Khizer Hsu, Chung-Chian Raja, Muhammad Asif Zahoor International Graduate School of Artificial Intelligence National Yunlin University of Science and Technology 123 University Road Section 3 Yunlin Douliou64002 Taiwan Department of Electrical and Computer Engineering International Islamic University Islamabad Pakistan Future Technology Research Center National Yunlin University of Science and Technology 123 University Road Section 3 Yunlin Douliou64002 Taiwan Department of Information Management National Yunlin University of Science and Technology 123 University Road Section 3 Yunlin Douliou64002 Taiwan

Population-based metaheuristic algorithms have gained significant attention in research community due to its effectiveness in solving complex optimization problems in diverse fields. In this study, knacks of population-based Runge-Kutta optimizer (RUN) are exploited for the identification of fractional input non-linear exogenous auto-regressive (FINARX) system with key term separation. The fractional order calculus operator of the Grünwald-Letnikov derivative is exploited to develop FINARX from a conventional non-linear auto-regressive exogenous system. The identification scheme for FINARX model is implemented through a mean-square-error-based fitness function. RUN utilizes the slope variations calculated by the well-known Runge-Kutta method for an effective search mechanism in the exploration and exploitation phases. Moreover, an enhanced solution quality mechanism is employed for speedy convergence and keeping the movement toward the best solution by escaping the local optima. The robustness of the algorithm is analyzed by multiple variations of non-linearity as well as different noise scenarios. The performance of the RUN to identify the FINARX system is validated in terms of convergence rate, fitness value, robustness, and accuracy in weight estimation. The effectiveness of the RUN is further assessed through exhaustive simulations with their statistics as well as comparison with the standard recent counterparts, including the Whale optimization algorithm, Reptile Search algorithm, and Aquila optimizer on different performance indices for the FINARX system. © 2024 Elsevier Ltd

关键词： Mean square error

来源：评论

学校读者我要写书评

暂无评论

A Novel Approach to Smart Grid Energy Management Using the Osprey Optimization Algorithm 4

A Novel Approach to Smart Grid Energy Management Using the O...

引用

4th International Conference on Sentiment Analysis and Deep Learning, ICSADL 2025

作者： Rudrapogu, Nissisolomon Hemalatha, N. Warkad, Sanjay B Jayanthi, A. Vinoth, K. Jayaram, B. Lecturer in Eee Nissisolomon Rudrapogu Mbts Government Polytechnic College Department of Electrical and Electronics Engineering Section Andhra Pradesh Guntur522005 India Bharath Institute of Higher Education and Research Department of Electrical and Electronics Engineering Tamil Nadu Chennai600073 India P. R. Pote Patil College of Engineering & Management Department of Electrical Engineering Maharashtra Amravati444602 India Jeppiaar Institute of Technology Department of Physics Tamil Nadu Sriperumbudur631502 India Vel Tech Rangarajan Dr. Sagunthala R&d Institute of Science and Technology Department of Electrical and Electronics Engineering Tamil Nadu Chennai600062 India Rmk Engineering College Department of Computer Science and Business Systems Tamil Nadu Thiruvallur601206 India

ISBN: (纸本)9798331523923

Smart Grid Energy Management (SGEM) denotes the function of optimizing energy flow in the grid while enhancing grid efficiency and stability. One major issue is that increased integration of Renewable Energy Sources (RESs) may add a layer of complexity to EM, which may, in turn, reduce the reliability and stability of the grid. Keeping such challenges in mind, this paper proposes the Osprey Optimization Algorithm (OOA) on its part to enhance SGEM through various facets of load balancing and energy distribution. The objective of this method is to minimize the Mean Absolute Percentage Error (MAPE), enhancing the precision of energy predictions and optimizing grid performance. The OOA optimizes energy distribution in micro grids, improving efficiency and reducing power losses. The performance of the suggested OOA method is assessed by contrasting it with other optimization approaches that are currently in use, including Particle Swarm Optimization (PSO), Multi Objective Genetic Algorithm (MOGA), Sparrow Search Algorithm (SSA), and Multi Objective Wind Driven Optimization (MOWDO). The OOA method is implemented on the MATLAB platform. The outcomes show that the proposed OOA method provides superior performance in minimizing MAPE, achieving the lowest MAPE value of 0.28%, indicating its enhanced accuracy in energy demand forecasting and optimization. © 2025 IEEE.

关键词： Clean energy

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：