检索结果-内蒙古大学图书馆

Modified Neural Network Used for Host Utilization Predication in Cloud computing Environment

Computers, Materials & Continua 2025年第3期82卷 5185-5204页

作者： Arif Ullah Siti Fatimah Abdul Razak Sumendra Yogarayan Md Shohel Sayeed Centre for Intelligent Cloud Computing Multimedia UniversityMelaka75450Malaysia Faculty of Information Science and Technology Multimedia UniversityMelaka75450Malaysia

Networking,storage,and hardware are just a few of the virtual computing resources that the infrastruc-ture service model offers,depending on what the client *** essential aspect of cloud computing that improves resource allocation techniques is host load *** difficulty means that hardware resource allocation in cloud computing still results in hosting initialization issues,which add several minutes to response *** solve this issue and accurately predict cloud capacity,cloud data centers use prediction *** permits dynamic cloud scalability while maintaining superior service *** host prediction,we therefore present a hybrid convolutional neural network long with short-term memory model in this ***,the suggested hybrid model is input is subjected to the vector auto regression *** data in many variables that,prior to analysis,has been filtered to eliminate linear *** that,the persisting data are processed and sent into the convolutional neural network layer,which gathers intricate details about the utilization of each virtual machine and central processing *** next step involves the use of extended short-term memory,which is suitable for representing the temporal information of irregular trends in time series *** key to the entire process is that we used the most appropriate activation function for this type of model a scaled polynomial constant *** systems require accurate prediction due to the increasing degrees of unpredictability in data *** of this,two actual load traces were used in this study’s assessment of the *** example of the load trace is in the typical dispersed *** comparison to CNN,VAR-GRU,VAR-MLP,ARIMA-LSTM,and other models,the experiment results demonstrate that our suggested approach offers state-of-the-art performance with higher accuracy in both datasets.

关键词： Cloud computing datacenter virtual machine(VM) predication algorithm

来源：评论

学校读者我要写书评

暂无评论

Behaviour-diverse automatic penetration testing:a coverage-based deep reinforcement learning approach

引用

Frontiers of Computer science 2025年第3期19卷 15-24页

作者： Yizhou YANG Longde CHEN Sha LIU Lanning WANG Haohuan FU Xin LIU Zuoning CHEN Zhongguancun Laboratory Beijing 100081China Zhejiang Lab Hangzhou 311121China National Research Centre of Parallel Computer Engineering and Technology Wuxi 214000China Faculty of Geographical Science Beijing Normal UniversityBeijing 100875China Department of Earth System Science Tsinghua UniversityBeijing 100084China

Reinforcement Learning(RL)is gaining importance in automating penetration testing as it reduces human effort and increases ***,given the rapidly expanding scale of modern network infrastructure,the limited testing scale and monotonous strategies of existing RLbased automated penetration testing methods make them less effective in practical *** this paper,we present CLAP(Coverage-Based Reinforcement Learning to Automate Penetration Testing),an RL penetration testing agent that provides comprehensive network security assessments with diverse adversary testing behaviours on a massive *** employs a novel neural network,namely the coverage mechanism,to address the enormous and growing action spaces in large *** also utilizes a Chebyshev decomposition critic to identify various adversary strategies and strike a balance between *** results across various scenarios demonstrate that CLAP outperforms state-of-the-art methods,by further reducing attack operations by nearly 35%.CLAP also provides enhanced training efficiency and stability and can effectively perform pen-testing over large-scale networks with up to 500 ***,the proposed agent is also able to discover pareto-dominant strategies that are both diverse and effective in achieving multiple objectives.

关键词： network security penetration testing reinforcement learning artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Hydrogen Energy Storage System:Review on Recent Progress

引用

Energy Engineering 2025年第1期122卷 1-39页

作者： MilleniumWong Hadi Nabipour Afrouzi Research Centre for Sustainable Technologies Faculty of EngineeringComputing and ScienceSwinburne University of TechnologyJalan Simpang TigaKuchingSarawak93350Malaysia College of Engineering Faculty of ComputingEngineering and the Built EnvironmentBirmingham City UniversityBirminghamWest MidlandsEnglandB47XGUK

A hydrogen energy storage system(HESS)is one of the many risingmodern green innovations,using excess energy to generate hydrogen and storing it for various *** that,there have been many discussions about commercializing HESS and improving it ***,the design and sizing process can be overwhelming to comprehend with various sources to examine,and understanding optimal design methodologies is crucial to optimize a HESS *** that,this review aims to collect and analyse a wide range of HESS studies to summarise recent *** different collections of studies are studied,one was sourced by the main author for preliminary readings,and another was obtained via *** findings from the Web of science platform were also examined for amore comprehensive *** findings include the People’sRepublic of China has been active in HESS research,as most works and active organizations originate from this *** has been mainly researched to support power generation and balance load demands,with financial analysis being the common scope of *** is a common tool used for HESS design,modelling,and optimization as it can handle complex *** neural network(ANN)has the potential to be used to model the HESS,but additional review is required as a formof future *** a commercialization perspective,pressurized hydrogen tanks are ideal for hydrogen storage in a HESS,but other methods can be considered after additional research and *** this review,it can be implied that modelling works will be the way forward for HESS research,but extensive collaborations and additional review are ***,this review summarized various takeaways that future research works on HESS can use.

关键词： Hydrogen energy storage system VOSViewer design review sizing

来源：评论

学校读者我要写书评

暂无评论

A comparative evaluation of augmented reality and virtual reality on chemistry experiment learning in higher level education

引用

Multimedia Tools and Applications 2024年 1-40页

作者： Lam, Meng Chun Majid, Nazatul Aini Abd Hassan, Nurul Izzaty Mobarak, Nadhratun Naiim Tan, Siok Yee Hashim, Harwati Liew, Sook Yee Soon, Daniel Abidin, Rimaniza Zainal Suwadi, Nur Asylah Mixed Reality and Pervasive Computing Lab Center for Artificial Intelligence Technology Faculty of Information Science & Technology Universiti Kebangsaan Malaysia Bangi43600 Malaysia Department of Chemical Sciences Faculty of Science and Technology Universiti Kebangsaan Malaysia Selangor Bangi43600 Malaysia Centre of Innovation in Teaching and Learning Faculty of Education Universiti Kebangsaan Malaysia Bangi43600 Malaysia Chemistry Division Centre for Foundation Studies in Science Universiti Malaya Kuala Lumpur50603 Malaysia Center for Software Technology and Management Faculty of Information Science & Technology Universiti Kebangsaan Malaysia Bangi43600 Malaysia

In the constantly evolving landscape of higher education, integrating cutting-edge technologies has become crucial for enhancing learning experiences. As advancements in Augmented Reality (AR) and Virtual Reality (VR) continue to redefine educational paradigms, it is essential to understand their unique contributions to Chemistry education. The objective of this study is to assess the impact of AR and VR technology on knowledge acquisition, performance, user acceptance, and motivation. This was achieved through a comparative analysis of AR and VR mobile applications in a learning environment for chemistry experiments. The evaluation involved three main phases: pre-test, post-test and exchange phase. A total of 32 participants were recruited for the between-subject evaluation. Each group completed demographic forms and knowledge tests to ensure balanced representation. Afterwards, the participants were required to complete the knowledge test and questionnaire in the post-test. While in the exchange phase, it was held to acquire participants’ preferences on the best application to conduct chemistry experiments. The results reveal significant findings for both groups, indicating that AR and VR applications offer enhanced learning experiences. The results showed significant improvements in knowledge acquisition for both AR and VR groups, with both AR and VR groups demonstrating a substantial increase in knowledge scores in the post-test phase. Notably, the AR score was 44% better than the VR group in the post-test phase. In addition, the participants expressed significantly greater satisfaction with AR than with VR, implying a higher level of comfort and contentment with AR technology for conducting chemistry experiments. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Virtual environments

来源：评论

学校读者我要写书评

暂无评论

Design and Development of a Small-Scale Green Hydrogen Vehicle:Hydrogen Consumption Analysis under Varying Loads for Zero-Emission Transport

引用

Energy Engineering 2025年第5期122卷 1788-1803页

作者： Perry Yang Tchie Hunn Hadi Nabipour Afrouzi Research Centre for Sustainable Technologies Faculty of EngineeringComputing and ScienceSwinburne University of TechnologyJalan Simpang TigaKuching93350SarawakMalaysia College of Engineering Faculty of ComputingEngineering and the Built EnvironmentBirmingham City UniversityBirminghamB47XGUK

With growing interest in its potential applications across both stationary and transportation sectors,hydrogen has emerged as a promising alternative for environmentally responsible power *** replacing traditional fuels,hydrogen can significantly reduce greenhouse gas emissions in the transportation *** study focuses on the design and downsizing of a green hydrogen fuel cell car,aiming to scale the concept for larger *** components,including fuel cells,electrolysers,and solar panels,were evaluated through extensive laboratory *** reveal that variations in sunlight impact the solar panel’shydrogenproductionrate,withdifferences of approximately 4.9%attributed to changes in time and *** of consumption rates showed that a 17.4%increase in current consumption leads to a significant reduction in operational *** testing under varying loads demonstrated that higher current demands,such as those from a DC motor,accelerate hydrogen depletion,whereas lower currents extend operational *** results underscore the importance of maximizing solar energy efficiency,reducing reliance on conventional energy sources,and regulating consumption rates to optimize fuel cell *** hydrogen is produced using renewable energy,fuel cell technology is virtually ***,the study highlights the viability of powering vehicles with renewable energy,emphasizing the potential of green hydrogen fuel cell technology as a sustainable transportation solution.

关键词： Environmentally sustainable small scale solar hydrogen fuel cell car

来源：评论

学校读者我要写书评

暂无评论

An Automated Real-Time Face Mask Detection System Using Transfer Learning with Faster-RCNN in the Era of the COVID-19 Pandemic

引用

Computers, Materials & Continua 2022年第5期71卷 4151-4166页

作者： Maha Farouk S.Sabir Irfan Mehmood Wafaa Adnan Alsaggaf Enas Fawai Khairullah Samar Alhuraiji Ahmed S.Alghamdi Ahmed A.Abd El-Latif Department of Information Systems Faculty of Computing and Information TechnologyKing Abdulaziz UniversitySaudi Arabia Centre for Visual Computing Faculty of Engineering and InformaticsUniversity of BradfordBradfordU.K Department of Information Technology Faculty of Computing and Information TechnologyKing Abdulaziz UniversityJeddahP.O.Box 23713Saudi Arabia Department of Computer Science Faculty of Computing and Information TechnologyKing Abdulaziz UniversityJeddahSaudi Arabia Department of Cybersecurity College of Computer Science and EngineeringUniversity of JeddahSaudi Arabia Department of Mathematics and Computer Science Faculty of ScienceMenoufia University32511Egypt

Today,due to the pandemic of COVID-19 the entire world is facing a serious health *** to the World Health Organization(WHO),people in public places should wear a face mask to control the rapid transmission of *** governmental bodies of different countries imposed that wearing a face mask is compulsory in public ***,it is very difficult to manually monitor people in overcrowded *** research focuses on providing a solution to enforce one of the important preventative measures of COVID-19 in public places,by presenting an automated system that automatically localizes masked and unmasked human faces within an image or video of an area which assist in this outbreak of *** paper demonstrates a transfer learning approach with the Faster-RCNN model to detect faces that are masked or *** proposed framework is built by fine-tuning the state-of-the-art deep learning model,Faster-RCNN,and has been validated on a publicly available dataset named Face Mask Dataset(FMD)and achieving the highest average precision(AP)of 81%and highest average Recall(AR)of 84%.This shows the strong robustness and capabilities of the Faster-RCNN model to detect individuals with masked and un-masked ***,this work applies to real-time and can be implemented in any public service area.

关键词： COIVD-19 deep learning faster-RCNN object detection transfer learning face mask

来源：评论

学校读者我要写书评

暂无评论

Unveiling Effective Heuristic Strategies: A Review of Cross-Domain Heuristic Search Challenge Algorithms

引用

Computer Modeling in Engineering & sciences 2025年第2期142卷 1233-1288页

作者： Mohamad Khairulamirin Md Razali MasriAyob Abdul Hadi Abd Rahman Razman Jarmin Chian Yong Liu Muhammad Maaya Azarinah Izaham Graham Kendall Faculty of Information Science and Technology Universiti Kebangsaan MalaysiaBangi43600SelangorMalaysia Center for Artificial Intelligence Technology Universiti Kebangsaan MalaysiaBangi43600SelangorMalaysia Faculty of Medicine Universiti Kebangsaan Malaysia Medical CentreCheras56000Kuala LumpurMalaysia School of Engineering and Computing MILA UniversityNilai71800Negeri SembilanMalaysia School of Computer Science University of Nottingham-Malaysia CampusSemenyih43500SelangorMalaysia

The Cross-domain Heuristic Search Challenge(CHeSC)is a competition focused on creating efficient search algorithms adaptable to diverse problem *** hyper-heuristics are a class of algorithms that dynamically choose heuristics during the search *** selection hyper-heuristics have different imple-mentation ***,comparisons between them are lacking in the literature,and previous works have not highlighted the beneficial and detrimental implementation methods of different *** question is how to effectively employ them to produce an efficient search ***,the algorithms that competed in the inaugural CHeSC have not been collectively *** work conducts a review analysis of the top twenty competitors from this competition to identify effective and ineffective strategies influencing algorithmic performance.A summary of the main characteristics and classification of the algorithms is *** analysis underlines efficient and inefficient methods in eight key components,including search points,search phases,heuristic selection,move acceptance,feedback,Tabu mechanism,restart mechanism,and low-level heuristic parameter *** review analyzes the components referencing the competition’s final leaderboard and discusses future research directions for these *** effective approaches,identified as having the highest quality index,are mixed search point,iterated search phases,relay hybridization selection,threshold acceptance,mixed learning,Tabu heuristics,stochastic restart,and dynamic *** are also compared with recent trends in *** work enhances the understanding of selection hyper-heuristics,offering valuable insights for researchers and practitioners aiming to develop effective search algorithms for diverse problem domains.

关键词： Hyper-heuristics search algorithms optimization heuristic selection move acceptance learning diversification parameter control

来源：评论

学校读者我要写书评

暂无评论

A Self-adaptive Step-size Search Algorithm for the Cardinality Constrained Portfolio Optimisation Problem 20

A Self-adaptive Step-size Search Algorithm for the Cardinali...

引用

20th IEEE International Colloquium on Signal Processing and Its Applications, CSPA 2024

作者： Loke, Zi Xuan Goh, Say Leng Likoh, Jonathan Universiti Malaysia Sabah Labuan International Campus Faculty Of Computing And Informatics Labuan Malaysia Universiti Malaysia Sabah Preparatory Centre For Science And Technology Sabah Malaysia

ISBN: (纸本)9798350382310

This paper proposes a Self-adaptive Step-size Search (SASS) algorithm to address a Cardinality Constrained Portfolio Optimisation Problem (CCPOP). The proposed methodology is tested using five datasets from OR-Library. Experiments are conducted to test different settings of the particles in the SASS algorithm. The computational results are compared in terms of performance measures. The SASS algorithm achieves a lower value for most of the performance measures when the number of particles increases. © 2024 IEEE.

关键词： Constrained optimization

来源：评论

学校读者我要写书评

暂无评论

Adsorption of 2,4-dichlorophenoxyacetic acid onto oil palm trunk-derived activated carbon: Isotherm and kinetic studies at acidic, ambient condition

引用

Materials Today: Proceedings 2022年 64卷 1557-1562页

作者： Mohd Noor Hazrin, Hanna Maizura Lim, Adeline Li, Claudia Chew, Jiuan Jing Sunarso, Jaka Research Centre for Sustainable Technologies Faculty of Engineering Computing and Science Swinburne University of Technology Jalan Simpang Tiga Sarawak Kuching93350 Malaysia

Adsorption represents an attractive method to remove pesticide from contaminated water given its relatively low cost and simple process. This work evaluates the adsorption isotherms and kinetics of 2,4-dichlorophenoxyacetic acid (2,4-D) onto oil palm trunk-derived activated carbon (OPT-AC). Batch adsorption was performed to determine the effects of pH, temperature, initial adsorbate concentration, and contact time. The highest removal efficiency was obtained at pH 2 due to the absence of electrostatic repulsion between the adsorbent and the adsorbate as indicated by the point of zero charge (pHpzc) of 4.8 for OPT-AC and a pKa of 2.73 for 2,4-D. The adsorption isotherm data at 25, 35, and 45 °C and pH of 2 can be fitted better by the non-linear Langmuir model relative to the non-linear Freundlich model. Langmuir monolayer maximum adsorption capacity was found to be 420.43 mg g−1, which lies among the highest reported values for activated carbon materials used for 2,4-D removal. Adsorption kinetic data at 35 °C and pH of 2, on the other hand, can be better correlated by pseudo-second order (PSO) kinetic model compared to pseudo-first order (PFO) model, which implies the more dominant presence of chemisorption relative to physisorption. The high adsorption uptake of 2,4-D by OPT-AC highlights its potential as an attractive alternative to commercial AC particularly for medium to large scale 2,4-D removal from acidic wastewater. © 2021

关键词： Activated carbon

来源：评论

学校读者我要写书评

暂无评论

Modeling and simulation study of oxygen permeation in La0.8Ca0.2Fe0.95O3-δ-Ag hollow fiber membrane module

引用

Materials Today: Proceedings 2022年 64卷 1549-1556页

作者： Yeo, Jason Yi Juang Li, Claudia Sunarso, Jaka Research Centre for Sustainable Technologies Faculty of Engineering Computing and Science Swinburne University of Technology Jalan Simpang Tiga KuchingSarawak93350 Malaysia

Mixed ionic-electronic conducting (MIEC) ceramic membranes present an attractive alternative oxygen separation technology to cryogenic distillation and pressure swing adsorption. The model of Tan and Li has been extensively adopted in the oxygen permeation modeling through MIEC hollow fiber membranes. To evaluate the performance of the La0.8Ca0.2Fe0.95O3-δ-Ag hollow fiber membrane module here, the oxygen permeation is simulated numerically by feeding the air into the shell while passing sweep gas or creating a vacuum in the permeate side under different configuration. The simulation results show that countercurrent flow configuration is preferable in the sweep gas mode given its capability to separate oxygen completely under moderate flow rate of feed air. For vacuum mode, both cocurrent and countercurrent flow configurations result in a similar oxygen permeation performance, which lies between the sweep gas mode with countercurrent and cocurrent flow configurations. When abundant oxygen presence is created in the feed side by elevating its flow rate, the sweep gas mode loses its oxygen separation efficiency and is thus outperformed by the vacuum mode. © 2022

关键词： Oxygen

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：