检索结果-内蒙古大学图书馆

Intelligent Framework Using IoT-Based WSNs for Wildfire Detection

IEEE ACCESS 2021年 9卷 48185-48196页

作者： Verma, Sandeep Kaur, Satnam Rawat, Danda B. Xi, Chen Alex, Linss T. Jhanjhi, Noor Zaman Dr BR Ambedkar Natl Inst Technol Jalandhar 144011 Punjab India Howard Univ Dept Elect Engn & Comp Sci Washington DC 20059 USA Nanjing Univ Sch Business Nanjing 210000 Peoples R China Albertian Inst Sci & Technol AISAT Dept Elect & Elect Engn Kochi 682022 Kerala India Taylors Univ Sch Comp Sci & Engn SCE Subang Jaya 47500 Malaysia

IoT-based WSNs have proved their significance in delivering critical information pertaining to hostile applications such as Wildfire Detection (WD) with the least possible delay. However, the sensor nodes deployed in such networks suffer from the perturbing concern of limited energy resources, restricting their potential in the successful detection of wildfire. To extenuate this concern, we propose an intelligent framework, Sleep scheduling-based Energy Optimized Framework (SEOF), that works in two folds. Firstly, we propose an energy-efficient Cluster Head (CH) selection employing a recently developed meta-heuristic method, Tunicate Swarm Algorithm (TSA), that optimizes the five novel fitness parameters by integrating them into its weighted fitness function. Secondly, we perform a sleep scheduling of closely-located sensor nodes based on the distance threshold calculated through a set of experiments. Sleep scheduling methodology plays a pivotal role in abating the number of data transmissions in SEOF. Finally, we simulate SEOF in MATLAB under different scenarios to examine its efficacy for the various performance metrics and scalability features. Our empirical results prove that SEOF has ameliorated the network stability period for two different scenarios of network parameters by 35.3% and 216% vis-a-vis CIRP.

关键词： Forestry Wireless sensor networks Routing Delays clustering algorithms Vegetation Genetic algorithms Cluster head (CH) energy efficiency IoT-based WSN sleep scheduling tunicate swarm algorithm (TSA) wildfire detection (WD)

来源：评论

学校读者我要写书评

暂无评论

Detecting Text Baselines in Historical Documents With Baseline Primitives

引用

IEEE ACCESS 2021年 9卷 93672-93683页

作者： Jia, Wei Ma, Chixiang Sun, Lei Huo, Qiang Univ Sci & Technol China Dept Elect Engn & Informat Sci Hefei 230026 Peoples R China Microsoft Res Asia Beijing 100080 Peoples R China

Previous deep learning based approaches to text baseline detection in historical documents usually take it as a semantic segmentation task. These methods adopt a fully convolutional neural network to predict baseline pixels first and then group them into lines by heuristic post-processing steps, which tends to suffer from a wrongly merged or wrongly split problem owing to limited context information provided by pixels. To address these issues, we introduce the concept of a baseline primitive, which is defined as a virtual bounding box centered at each baseline pixel. After baseline primitive detection, a relation network is used to predict a link relationship for each pair of primitives. Consequently, text baselines are generated by detecting baseline primitives and grouping them with the corresponding link relationships. Owing to the design of baseline primitives, wider context information can be leveraged to improve link prediction accuracy. Therefore, our approach can effectively detect text baselines with small inter-line or large inter-word spacing. Quantitative experimental results demonstrate the effectiveness of the proposed baseline primitive design. Our approach achieves state-of-the-art performance on two public benchmarks, namely cBAD 2017 and cBAD 2019.

关键词： Layout Benchmark testing Degradation clustering algorithms Visualization Licenses Deep learning Handwritten documents historical documents text baseline detection baseline primitive

来源：评论

学校读者我要写书评

暂无评论

A Survey on WSN Issues with its Heuristics and Meta-Heuristics Solutions

引用

WIRELESS PERSONAL COMMUNICATIONS 2021年第1期121卷 745-814页

作者： Srivastava, Ankita Mishra, Pramod Kumar Banaras Hindu Univ Inst Sci Dept Comp Sci Varanasi Uttar Pradesh India

A wireless sensor networks (WSN's) has stimulated significant research work among the researchers in monitoring and tracking tasks. It's a quite challenging task that needs to cope up with various conflicting issues such as energy efficiency, network lifetime, connectivity, coverage, etc. in WSN's for designing various applications. This paper explores the recent work and efforts done in addressing the various issues in WSN's. This paper focused on basic concepts regarding the WSN's and discusses meta-heuristics and heuristics algorithms for solving these issues with recent investigations. Various optimization algorithms in the context of WSN, routing algorithms, and clustering algorithms were discussed with details of earlier work done. This paper delivers various Multi-Objective Optimization approaches deeply for solving issues and summarizes the recent research work and studies. It provides researchers an understanding of the various issues, trade-offs between them, and meta-heuristics and heuristics approach for solving these issues. A glimpse of open research challenges has also been provided which will be helpful for researchers. This paper also gives an insight into various issues, open challenges that still exist in WSN's with their heuristics and meta-heuristics solutions and also focuses on various conflicting issues as well.

关键词： Multi-objective optimization (MOO) Issues trade-off Wireless sensor networks (WSN's) Pareto-optimal solution Hierarchical routing QoS clustering algorithms Heterogeneous network

来源：评论

学校读者我要写书评

暂无评论

Unsupervised algorithms to Detect Zero-Day Attacks: Strategy and Application

引用

IEEE ACCESS 2021年 9卷 90603-90615页

作者： Zoppi, Tommaso Ceccarelli, Andrea Bondavalli, Andrea Univ Florence Dept Math & Informat I-50134 Florence Italy

In the last decade, researchers, practitioners and companies struggled for devising mechanisms to detect cyber-security threats. Among others, those efforts originated rule-based, signature-based or supervised Machine Learning (ML) algorithms that were proven effective for detecting those intrusions that have already been encountered and characterized. Instead, new unknown threats, often referred to as zero-day attacks or zero-days, likely go undetected as they are often misclassified by those techniques. In recent years, unsupervised anomaly detection algorithms showed potential to detect zero-days. However, dedicated support for quantitative analyses of unsupervised anomaly detection algorithms is still scarce and often does not promote meta-learning, which has potential to improve classification performance. To such extent, this paper introduces the problem of zero-days and reviews unsupervised algorithms for their detection. Then, the paper applies a question-answer approach to identify typical issues in conducting quantitative analyses for zero-days detection, and shows how to setup and exercise unsupervised algorithms with appropriate tooling. Using a very recent attack dataset, we debate on i) the impact of features on the detection performance of unsupervised algorithms, ii) the relevant metrics to evaluate intrusion detectors, iii) means to compare multiple unsupervised algorithms, iv) the application of meta-learning to reduce misclassifications. Ultimately, v) we measure detection performance of unsupervised anomaly detection algorithms with respect to zero-days. Overall, the paper exemplifies how to practically orchestrate and apply an appropriate methodology, process and tool, providing even non-experts with means to select appropriate strategies to deal with zero-days.

关键词： Classification algorithms Anomaly detection clustering algorithms Training Machine learning algorithms Security Intrusion detection Zero-day attacks intrusion detection machine learning anomaly detection RELOAD security unsupervised learning cyber-attacks

来源：评论

学校读者我要写书评

暂无评论

Cluster Analysis of Mixed and Missing Chronic Kidney Disease Data in KwaZulu-Natal Province, South Africa

引用

IEEE ACCESS 2021年 9卷 52125-52143页

作者： Popoola, Peter A. Tapamo, Jules-Raymond Assounga, Alain G. Univ KwaZulu Natal Sch Math Stat & Comp Sci Westville Campus ZA-4041 Durban South Africa Univ KwaZulu Natal Sch Engn Howard Coll Campus ZA-4041 Durban South Africa Univ KwaZulu Natal Nelson Mandela Sch Med Dept Nephrol ZA-4001 Durban South Africa Inkosi Albert Luthuli Cent Hosp ZA-4091 Durban South Africa

Real-world datasets, particularly Electronic Health Records, are routinely found to be mixed (comprised of both categorical and continuous variables) and/or missing in nature. Such datasets present peculiar challenges related both to their clustering and the evaluation of the clusterings obtained. In this paper, we discuss these challenges in detail, as well as the solution approaches applied to them in the literature. We then apply some of these approaches to a multi-racial Chronic Kidney Disease (CKD) dataset comprising of 20 continuous and 12 categorical variables with an over 30% missingness ratio, evaluating our results through external and internal validation as well as cluster stability testing. From the results of our study, the Ahmad-Dey distance measure consistently outperformed Gower's distance on our mixed and missing dataset. In addition, our results show that advanced imputation methods like multiple imputation, which take into consideration the uncertainty inherent in imputation, should be explored when clustering missing datasets. Three clusters were identified from our dataset which were significantly differentiated by age, sex, estimated Glomerular Filtration Rate (eGFR), creatinine, urea, and hemoglobin, but not by race or blood pressure. The fact that, through proper cluster analysis, we were unable to identify five clusters corresponding to the five CKD stages usually used to classify CKD patients indicates that datasets with more than the usual four/six variables used for computing eGFR may contain a latent structure different from this five-group structure, the identification of which will provide valuable insights peculiar to each cohort for medical practitioners.

关键词： clustering algorithms Dimensionality reduction Prototypes Kidney Diseases Weight measurement Electronic medical records Chronic kidney disease cluster analysis electronic health records missing data mixed data Gower’ s distance Ahmad-Dey distance

来源：评论

学校读者我要写书评

暂无评论

Cluster Prediction for Opinion Dynamics From Partial Observations

引用

IEEE TRANSACTIONS ON SIGNAL AND INFORMATION PROCESSING OVER NETWORKS 2021年 7卷 101-113页

作者： Zhang, Zehong Lu, Fei Johns Hopkins Univ Dept Math Baltimore MD 21218 USA

We present a Bayesian approach to predict the clustering of opinions for a system of interacting agents from partial observations. The Bayesian formulation overcomes the unobservability of the system and quantifies the uncertainty in the prediction. We characterize the clustering by the posterior of the clusters' sizes and centers, and we represent the posterior by samples. To overcome the challenge in sampling the high-dimensional posterior, we introduce an auxiliary implicit sampling (AIS) algorithm using two-step observations. Numerical results show that the AIS algorithm leads to accurate predictions of the sizes and centers for the leading clusters, in both cases of noiseless and noisy observations. In particular, the centers are predicted with high success rates, but the sizes exhibit a considerable uncertainty that is sensitive to observation noise and the observation ratio.

关键词： Bayes methods Prediction algorithms Trajectory Heuristic algorithms clustering algorithms Artificial intelligence Uncertainty Bayesian approach clustering prediction opinion dynamics sequential Monte Carlo state space model

来源：评论

学校读者我要写书评

暂无评论

Multiplex Graph clustering with Network Embedding Technique: Review, Methods and Challenges

Multiplex Graph Clustering with Network Embedding Technique:...

引用

2021 IEEE International Conference on Unmanned Systems, ICUS 2021

作者： Han, Beibei Wei, Yingmei Wang, Xianghan Wang, Qingyong College of Systems Engineering National University of Defense Technology Changsha China

ISBN: (纸本)9780738146577

Multiplex graph clustering with network embedding technique has received considerable attention recently. The multiplex graph, a special multilayer network, can model the various interactions among similar entities, and it can describe more comprehensive information than the traditional single-layer network. In this paper, we study the multiplex graph clustering methods with network embedding technique, which aims at learning low-dimensional embedding for each node in the graph. The obtained node representations can be inputted into the clustering algorithm to generate the graph clustering result. We first reviewed the single-layer and multiplex network embedding techniques for the multiplex graph clustering. Then, we present some important multiplex network datasets for evaluating the proposed clustering methods, and describe some common evaluation methods. Finally, the pros and cons of these method, and challenges are discussed. © 2021 IEEE.

关键词： clustering algorithms

来源：评论

学校读者我要写书评

暂无评论

Financial Advisor Recruitment: A Smart Crowdsourcing-Assisted Approach

引用

IEEE TRANSACTIONS ON COMPUTATIONAL SOCIAL SYSTEMS 2021年第3期8卷 682-688页

作者： Hamadi, Raby Ghazzai, Hakim Besbes, Hichem Massoud, Yehia Stevens Inst Technol Sch Syst & Enterprises Hoboken NJ 07030 USA Univ Carthage Higher Sch Commun Tunis Tunis 2083 Tunisia

Successful portfolio management requires, in addition to advanced optimization strategies, effective recruitment of specialized financial advisors. Hiring the wrong ones can be detrimental to investors' financial goals. In this article, we propose an automated crowdsourcing system to organize cooperation between financial advisors and investors. Without interfering with their private portfolio optimization techniques, we design a recruitment framework that matches financial advisors to investors based on their profiles and features, as well as the previous activities of their peers. Using the database of the crowdsourcing platform, we employ an unsupervised technique to regroup advisors with a high degree of similarities into clusters and, hence, shrink the search space. Afterward, we train a machine learning regression model to predict the matching score that can be achieved if an investor hires a particular advisor. These scores are converted to weights of bipartite graphs to which we apply a double-phased many-to-many maximum weight matching algorithm to determine a suitable investor-advisor combination. In the simulations, we investigate the performance of the proposed recruitment approach and show that, compared with other traditional approaches, higher returns can be reached for both investors and financial advisors.

关键词： Crowdsourcing Portfolios Recruitment clustering algorithms Prediction algorithms Optimization Regression tree analysis Crowdsourcing financial technology machine learning (ML) portfolio optimization

来源：评论

学校读者我要写书评

暂无评论

Kernel Matrix Approximation on Class-Imbalanced Data With an Application to Scientific Simulation

引用

IEEE ACCESS 2021年 9卷 83579-83591页

作者： Hajibabaee, Parisa Pourkamali-Anaraki, Farhad Hariri-Ardebili, Mohammad Amin Univ Massachusetts Lowell Dept Comp Sci Lowell MA 01854 USA Univ Colorado Dept Civil Engn Boulder CO 80309 USA Univ Maryland Coll Comp Math & Nat Sci College Pk MD 20742 USA

Generating low-rank approximations of kernel matrices that arise in nonlinear machine learning techniques holds the potential to significantly alleviate the memory and computational burdens. A compelling approach centers on finding a concise set of exemplars or landmarks to reduce the number of similarity measure evaluations from quadratic to linear concerning the data size. However, a key challenge is to regulate tradeoffs between the quality of landmarks and resource consumption. Despite the volume of research in this area, current understanding is limited regarding the performance of landmark selection techniques in the presence of class-imbalanced data sets that are becoming increasingly prevalent in many applications. Hence, this paper provides a comprehensive empirical investigation using several real-world imbalanced data sets, including scientific data, by evaluating the quality of approximate low-rank decompositions and examining their influence on the accuracy of downstream tasks. Furthermore, we present a new landmark selection technique called Distance-based Importance Sampling and clustering (DISC), in which the relative importance scores are computed for improving accuracy-efficiency tradeoffs compared to existing works that range from probabilistic sampling to clustering methods. The proposed landmark selection method follows a coarse-to-fine strategy to capture the intrinsic structure of complex data sets, allowing us to substantially reduce the computational complexity and memory footprint with minimal loss in accuracy.

关键词： Kernel Eigenvalues and eigenfunctions Task analysis clustering algorithms Matrix decomposition Memory management Machine learning Classification algorithms computational complexity data compression pattern analysis unsupervised learning

来源：评论

学校读者我要写书评

暂无评论

Fairness-Aware Energy Efficient Scheduling on Heterogeneous Multi-Core Processors

引用

IEEE TRANSACTIONS ON COMPUTERS 2021年第1期70卷 72-82页

作者： Salami, Bagher Noori, Hamid Naghibzadeh, Mahmoud Ferdowsi Univ Mashhad Dept Comp Engn Mashhad *** Razavi Khorasan Iran

Heterogeneous multi-core processors (HMP) with the same instruction set architecture (ISA) integrate complex high performance big cores with power efficient small cores on the same chip. In comparison with homogeneous architectures, HMPs have been shown to significantly increase energy efficiency. However, current techniques to exploit the energy efficiency of HMPs do not consider fair usage of resources that leads to reduced performance predictability, a longer makespan, starvation, and QoS degradation. The effect of different cluster voltage and frequency levels on fairness is another issue neglected by previous task scheduling algorithms. The present study investigates both the fairness problem and energy efficiency in HMPs. This article proposes a heterogeneous fairness-aware energy efficient framework (HFEE) that employs DVFS to meet fairness constraints and provide energy efficient scheduling. The proposed framework is implemented and evaluated on a real heterogeneous multi-core processor. The experimental results indicate that the introduced technique can significantly improve energy efficiency and fairness when compared to Linux standard scheduler and two energy efficient and fairness-aware schedulers.

关键词： Energy efficiency Task analysis Multicore processing Processor scheduling Program processors clustering algorithms Energy efficient scheduling fair scheduling heterogeneous multi-core big LITTLE architecture

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

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

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：