检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Schneider, Dominic Rapp, Lutz Ament, Christoph Advanced Technology Adtran Meiningen98617 Germany Faculty of Applied Computer Science University of Augsburg Augsburg86159 Germany

This article proposes a novel fuzzy clustering based anomaly detection method for pump current time series of EDFA systems. The proposed change detection framework (CDF) strategically combines the advantages of entropy analysis (EA) and principle component analysis (PCA) with fuzzy clustering procedures. In the framework, EA is applied for dynamic selection of features for reduction of the feature space and increase of computational performance. Furthermore, PCA is utilized to extract features from the raw feature space to enable generalization capability of the subsequent fuzzy clustering procedures. Three different fuzzy clustering methods, more precisely the fuzzy clustering algorithm, a probabilistic clustering algorithm and a possibilistic clustering algorithm are evaluated for performance and generalization. Hence, the proposed framework has the innovative feature to detect changes in pump current time series at an early stage for arbitrary points of operation, compared to state-of-the-art predefined alarms in commercially used EDFAs. Moreover, the approach is implemented and tested using experimental data. In addition, the proposed framework enables further approaches of applying decentralized predictive maintenance for optical fiber networks. Copyright © 2024, The Authors. All rights reserved.

关键词： Predictive maintenance

来源：评论

学校读者我要写书评

暂无评论

SSABA:Search Step Adjustment Based Algorithm

引用

computers, Materials & Continua 2022年第6期71卷 4237-4256页

作者： Fatemeh Ahmadi Zeidabadi Ali Dehghani Mohammad Dehghani Zeinab Montazeri Stepán Hubálovsky Pavel Trojovsky Gaurav Dhiman Department of Mathematics and Computer Sciences Sirjan University of TechnologySirjanIran Department of Civil Engineering Islamic Azad UniversityEstahban BranchEstahbanIran Department of Mathematics Faculty of ScienceUniversity of Hradec KrálovéHradec Králové50003Czech Republic Department of Electrical and Electronics Engineering Shiraz University of TechnologyShirazIran Department of Applied Cybernetics Faculty of ScienceUniversity of Hradec KrálovéHradec Králové50003Czech Republic Department of Computer Science Government Bikram College of CommercePatialaPunjabIndia

Finding the suitable solution to optimization problems is a fundamental challenge in various *** algorithms are one of the effective stochastic methods in solving optimization *** this paper,a new stochastic optimization algorithm called Search StepAdjustment Based Algorithm(SSABA)is presented to provide quasi-optimal solutions to various optimization *** the initial iterations of the algorithm,the step index is set to the highest value for a comprehensive search of the search ***,with increasing repetitions in order to focus the search of the algorithm in achieving the optimal solution closer to the global optimal,the step index is reduced to reach the minimum value at the end of the algorithm *** is mathematically modeled and its performance in optimization is evaluated on twenty-three different standard objective functions of unimodal and multimodal *** results of optimization of unimodal functions show that the proposed algorithm SSABA has high exploitation power and the results of optimization of multimodal functions show the appropriate exploration power of the proposed *** addition,the performance of the proposed SSABA is compared with the performance of eight well-known algorithms,including Particle Swarm Optimization(PSO),Genetic Algorithm(GA),Teaching-Learning Based Optimization(TLBO),Gravitational Search Algorithm(GSA),Grey Wolf Optimization(GWO),Whale Optimization Algorithm(WOA),Marine Predators Algorithm(MPA),and Tunicate Swarm Algorithm(TSA).The simulation results show that the proposed SSABA is better and more competitive than the eight compared algorithms with better performance.

关键词： Optimization population-based optimization problem search step optimization algorithm minimization maximization

来源：评论

学校读者我要写书评

暂无评论

A Wild Sheep Chase Through an Orchard

arXiv

引用

arXiv 2024年

作者： Dempsey, Jordan van Iersel, Leo Jones, Mark Murakami, Yukihiro Zeh, Norbert Faculty of Computer Science Dalhousie University Halifax Canada Delft Institute of Applied Mathematics Delft University of Technology Netherlands

Orchards are a biologically relevant class of phylogenetic networks as they can describe treelike evolutionary histories augmented with horizontal transfer events. Moreover, the class has attractive mathematical characterizations that can be exploited algorithmically. On the other hand, undirected orchard networks have hardly been studied yet. Here, we prove that deciding whether an undirected, binary phylogenetic network is an orchard—or equivalently, whether it has an orientation that makes it a rooted orchard—is NP-hard. For this, we introduce a new characterization of undirected orchards which could be useful for proving positive results. Copyright © 2024, The Authors. All rights reserved.

关键词： Orchards

来源：评论

学校读者我要写书评

暂无评论

Streamlining Task Planning Systems for Improved Enactment in Contemporary Computing Surroundings

引用

SN computer science 2024年第8期5卷 1-9页

作者： Menon, Sindhu Addula, Santosh Reddy Parkavi, A. Subbalakshmi, Ch. Dhandayuthapani, V. Bala Pokkuluri, Kiran Sree Soni, Anita School of Computing and Information Technology REVA University Karnataka Bangalore India Department of Information Technology University of the Cumberlands Williamsburg KY United States Dept of CSE M S Ramaiah Institute of Technology Bangalore India Department of Computer Science and Engineering Guru Nanak Institution Technical Campus (Autonomous) Ibrahimpatnam Ranga Reddy District Telagana State Hyderabad 501506 India Department of IT College of Computing and Information Sciences University of Technology and Applied Sciences Shinas Campus Oman Department of Computer Science and Engineering Shri Vishnu Engineering College for Women Bhimavaram India CSE Department IES University Bhopal Madhya Pradesh Bhopal India

Task planning algorithms are essential for maximizing efficiency and enhancing performance in modern computing systems, given the escalating demand for computational resources. This paper delves into the effectiveness of various scheduling algorithms across different computing environments, characterized by their unique workload dynamics and resource limitations. This method integrates adaptive algorithms and machine learning to dynamically optimize task planning, enhancing performance and efficiency in cloud, IoT, and distributed computing environments. These algorithms are crucial for optimizing key factors such as task completion times, job prioritization, and resource allocation while also addressing quality of service (QoS), cost, reliability, and specific resource needs. One significant challenge is that many task scheduling approaches do not account for the potential failure of tasks or resources. While some strategies effectively reduce overall completion time (makespan), they can result in severe workload imbalances. To address these issues, our study proposes a new approach that harnesses the processing capabilities of grid systems, thus boosting application performance and throughput. Our algorithm particularly focuses on balancing workload and accelerating scheduling operations, even in the face of grid node failures, by incorporating QoS metrics. This allows for a more robust and adaptable scheduling solution. Comparative analysis with existing methods demonstrates that our algorithm not only improves resource utilization but also significantly diminishes flow time and makespan, confirming its efficacy. Through this research, we contribute to the evolving field of autonomous task scheduling, presenting a solution that responds dynamically to changing environmental conditions and workload demands. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2024.

关键词： CPU Flow time Makespan MSHA QoS

来源：评论

学校读者我要写书评

暂无评论

Game Theory-Based IoT Efficient Power Control in Cognitive UAV

引用

computers, Materials & Continua 2022年第7期72卷 1561-1578页

作者： Fadhil Mukhlif Norafida Ithnin Omar B.Abdulghafoor Faiz Alotaibi Nourah Saad Alotaibi Information Assurance and Security Research Group(IASRG) School of ComputingFaculty of EngineeringUniversiti Teknologi MalaysiaJohorMalaysia Electronic and Telecommunication Department College of EngineeringThe American University of KurdistanIraq Faculty of Computer Science and Information Technology Universiti Putra MalaysiaSelangorMalaysia Computer Department Faculty of Applied CollegeImam Abdulrahman Bin Faisal UniversityDammamSaudi Arabia

With the help of network densification,network coverage as well as the throughput can be improved via ultra-dense networks(UDNs).In tandem,Unmanned Aerial Vehicle(UAV)communications have recently garnered much attention because of their high agility as well as widespread *** this paper,a cognitive UAV is proposed for wireless nodes power pertaining to the IoT ground ***,the UAV is included in the IoT system as the source of power for the wireless nodes as well as for resource *** quality of service(QoS)related to the cognitive node was considered as a utility function based on pricing scheme that was modelled as a non-cooperative game theory in order to maximise users’net utility ***,an energy efficiency non-cooperative game theory power allocation with pricing scheme(EE-NGPAP)is proposed to obtain an efficient power control within IoT wireless ***,uniqueness and existence of the Nash equilibrium have been demonstrated mathematically and through *** results show that the proposed energy harvest algorithm demonstrated considerable decrease in transmitted power consumption in terms of average power reduction,which is regarded to be apt with the 5Gnetworks’***,the proposed algorithm requires around 4 iterations only to converge to NE which makes the algorithm more suitable in practical heterogeneous scenarios.

关键词： UAV drones WSN IoT game theory energy efficiency 5G&B5G networks

来源：评论

学校读者我要写书评

暂无评论

A novel cooperative collision avoidance system for vehicular communication based on deep learning

引用

International Journal of Information technology (Singapore) 2024年第3期16卷 1661-1675页

作者： Farhat, Wajdi Ben Rhaiem, Olfa Faiedh, Hassene Souani, Chokri Laboratory of Microelectronics and Instrumentation University of Monastir Monastir Tunisia Higher Institute of Applied Sciences and Technology Sousse University Sousse Tunisia Computer Science Department College of Science Northern Border University Arar Saudi Arabia Digital Research Center of SFax (CRNS) SM@RTS (Laboratory of Signals systeMs aRtificial Intelligence and neTworkS) Sfax Tunisia

Global road traffic injuries represent a significant safety challenge, with the highest fatality rates worldwide stemming from a combination of drivers' reckless behavior and the ever-expanding number of vehicles on the roads. In light of these factors, Autonomous Vehicles (AVs) have received a lot of attention as a technology that has the potential to revolutionize various industries and solve a lot of problems. The rise of the Internet of Vehicles (IoV) and Connected Vehicles (CVs) enables AVs to perceive and react swiftly in complex road scenarios, prioritizing safety. These vehicles prioritize individual safety in all situations, significantly enhancing road safety. Mobile Edge Computing (MEC) plays a crucial role thanks to its capacity for minimal latency and high bandwidth capabilities, enabling critical vehicular applications. In this paper, we introduce a cooperative collision avoidance system based on MEC, named 2CAS-MEC, that proactively identifies and locates road hazards. Our system is based on MEC servers positioned alongside roads, it consistently analyzes traffic and hazard data, issuing targeted alerts to nearby vehicles regarding potential risks. Particularly, our work introduces an advanced deep learning system that utilizes 5G, mobile edge computing, and cloud intelligence to prevent vehicle collisions. The experimental results show that our system outperforms the existing related works and exhibits the anticipated performance, effectively helping drivers in accident avoidance. © 2023, The Author(s), under exclusive licence to Bharati Vidyapeeth's Institute of computer Applications and Management.

关键词： Cloud Connected and autonomous vehicles Deep learning IOV MEC Vehicle to-everything (V2X)

来源：评论

学校读者我要写书评

暂无评论

Analytical Study of Models in Quantum Field Theory: Fractional Kundu-Eckhaus and Massive Thirring Equations

引用

Nonlinear Dynamics 2025年 1-20页

作者： Izadi, Mohammad Patel, Yogeshwari F. Department of Applied Mathematics Faculty of Mathematics and Computer Shahid Bahonar University of Kerman Kerman Iran Department of Mathematical Sciences P D Patel Institute of Applied Sciences Charotar University of Science and Technology Changa India

This paper delves into the analytical study of two significant nonlinear fractional-order models in the Liouville-Caputo sense, which play a crucial role in the mathematical formulation of quantum field theory, particularly in describing anomalous diffusion and nonlocal interactions. The two models considered are the fractional-order massive Thirring model (FMTM) and the fractional-order Kundu-Eckhaus equation (FKEE). These models provide insights into natural events, such as the stability and dynamics of quantum solitons, rogue waves, and coherent quantum states in coupled quantum fields. Fractional orders in the FKEE highlight their impact on wave dispersion and memory effects, influencing the propagation and stability of quantum solitons. Similarly, the FMTM captures the intricate interplay between linear and nonlinear interactions, showcasing oscillatory behavior and emergent coherence in quantum systems. Using the Fractional Reduced Differential Transform Method (FRDTM), semi-analytical approximations are derived for both models, demonstrating the method’s efficacy in reducing computational complexity while maintaining high accuracy. The study emphasizes the role of fractional-order Liouville-Caputo derivative in encapsulating nonlocality and time-dependent memory effects, offering a deeper understanding of complex quantum dynamics and their applications in advanced optical systems, plasma physics, and quantum information science.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Decentralized Federated Learning Loop with Constrained Trust Mechanism 1

引用

22nd International Conference on Artificial Intelligence and Soft Computing, ICAISC 2023

作者： Polap, Dawid Prokop, Katarzyna Srivastava, Gautam Chun-Wei Lin, Jerry Faculty of Applied Mathematics Silesian University of Technology Kaszubska 23 Gliwice44-100 Poland Department of Mathematics and Computer Science Brandon University BrandonR7A 6A9 Canada Western Norway University of Applied Sciences Bergen Norway

ISBN: (数字)9783031425059

ISBN: (纸本)9783031425042

Federated learning has made it possible to introduce parallel training of deep neural networks by multiple users. The use of model aggregation contributes to the generalization of it, although there is a possibility of attacks. An example of this is dataset poisoning. Hence, in this research paper, we propose the introduction of a constrained trust mechanism for individual clients. In addition, a decentralized approach makes it possible to increase the effectiveness of the training process by removing the server and reducing the risk of an attack on the transmitting model. The proposed modification of federated learning was subjected to performance tests and compared with other known solutions. The obtained results indicate an increase in safety and accuracy. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

An Efficient Deep Learning Framwork for Classification and Detection of Anomaly Based Network Intrusion using NSL-KDD Dataset

An Efficient Deep Learning Framwork for Classification and D...

引用

Disruptive Technologies (ICDT), International Conference on

作者： Parth Mehrotra Uttkarsh Dwivedi Department of Computer Science and Enginnering G.L. Bajaj Institute of Technology and Management Gr. Noida India Department of Applied Computer Science and Enginnering G.L. Bajaj Institute of Technology and Management Gr. Noida India

ISBN: (数字)9798331519582

ISBN: (纸本)9798331519599

The past few years have seen unprecedented growth in the realms of technology and networking, as well as the proliferation of Internet services across all industries and regions. Because of rising instances of piracy and the compromise of several cutting-edge systems, it is crucial that we build information security tools capable of identifying emerging threats. An Intrusion Detection System (IDS) that use deep learning (DL) methods to identify network anomalies is a crucial piece of information security technology. The purpose of this study is to look at DL techniques and see if they can be used in an anomaly-based IDS. The purpose of this research is to employ a hybrid model Gated Recurrent Unit (GRU), Long Short-Term Memory (LSTM), & and (Convolutional Neural Networks (CNN) to identify the unknown assault package in a state-of-the-art IDS with high network performance. Standard classification metrics were used to evaluate DL models trained on the NSL-KDD dataset. These metrics included recall, f1- score, precision, and accuracy of categorization. We used the NSL-KDD dataset to fit and assess the flow. The model's outstanding producing abilities and excellent incursion identification performance are made possible by these data characteristics. Attack detection in the NSL-KDD dataset may be accomplished in two ways: binary classification and multiclass classification. Positive outcomes have been seen when applying the suggested strategy to multiclass classification (98% accuracy) and binary classification (99.99 percent accuracy). IDS have shown encouraging results from experiments using deep IDS models. According on the results of the research, the proposed approach outperforms the competing methodologies.

关键词： Deep learning Measurement Accuracy Web and internet services NSL-KDD Stability analysis Convolutional neural networks Long short term memory Standards Resilience

来源：评论

学校读者我要写书评

暂无评论

An Implementation of Stochastic Resonance based Machine Translation Model for Low Resource Languages using Novel Attention Models

An Implementation of Stochastic Resonance based Machine Tran...

引用

Disruptive Technologies (ICDT), International Conference on

作者： Rituraj Dixit Sarabjeet Singh Bedi Richa Agarwal MJP Rohilkhand University Bareilly Computer Science and Engineering Department (Applied Science) G.L. Bajaj Institute of Technology and Management Greater Noida

ISBN: (数字)9798331519582

ISBN: (纸本)9798331519599

In this paper we have proposed a new model in which the stochastic resonance technique is used to include white noise in the cell state and hidden state vectors of the LSTM model. A novel attention calculation technique is also being used in which cell state vectors are also used for attention score calculation. Earlier only hidden state or short-term memory vectors were used or attention score calculation, but in this novel approach we have used both cell state and hidden state vectors for attention score calculation. The encoder-decoder model which we have used produces better results than earlier models on the low-resource Indian languages.

关键词： Art Stochastic resonance Stochastic processes White noise Transformers Vectors Decoding Machine translation Disruptive technologies Long short term memory

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：