Identifying Control and Management Plane Poison Message Failure by K-Nearest Neighbor Method

Du, Xiaojiang

doi:10.1007/s10922-006-9027-8

Cited by 5 publications

(6 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The main elements of collected biochar samples were firstly determined by X-ray energy dispersive spectrometer, the LIBS data of which were employed to classify the calibration samples using the unsupervised hierarchical clustering method [ 26 ]. Similarly, the prediction samples were divided into various classifications of calibration samples on the basis of a supervised KNN algorithm [ 27 ]. Multiple classification regression models of PLSR [ 40 ] were developed and compared, of which the model with the best calibration performance was employed for quantitative prediction.…”

Section: Experimental Design and Methodsmentioning

confidence: 99%

“…It uses an unsupervised hierarchical clustering method [ 26 ] to classify calibration samples based on the main elemental LIBS data, and develops multiple regression models for different matrix classifications. Then, the prediction samples are divided into diverse classifications of calibration samples by supervised KNN algorithm [ 27 ], and a quantitative prediction is made based on the best matrix classification regression model.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Quantitative Detection of Chromium Pollution in Biochar Based on Matrix Effect Classification Regression Model

et al. 2021

View full text Add to dashboard Cite

Returning biochar to farmland has become one of the nationally promoted technologies for soil remediation and improvement in China. Rapid detection of heavy metals in biochar derived from varied materials can provide a guarantee for contaminated soil, avoiding secondary pollution. This work aims first to apply laser-induced breakdown spectroscopy (LIBS) for the quantitative detection of Cr in biochar. Learning from the principles of traditional matrix effect correction methods, calibration samples were divided into 1–3 classifications by an unsupervised hierarchical clustering method based on the main elemental LIBS data in biochar. The prediction samples were then divided into diverse classifications of calibration samples by a supervised K-nearest neighbor (KNN) algorithm. By comparing the effects of multiple partial least squares regression (PLSR) models, the results show that larger numbered classifications have a lower averaged relative standard deviations of cross-validation (ARSDCV) value, signifying a better calibration performance. Therefore, the 3 classification regression model was employed in this study, which had a better prediction performance with a lower averaged relative standard deviations of prediction (ARSDP) value of 8.13%, in comparison with our previous research and related literature results. The LIBS technology combined with matrix effect classification regression model can weaken the influence of the complex matrix effect of biochar and achieve accurate quantification of contaminated metal Cr in biochar.

show abstract

Section: Experimental Design and Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Quantitative Detection of Chromium Pollution in Biochar Based on Matrix Effect Classification Regression Model

et al. 2021

View full text Add to dashboard Cite

show abstract

“…In [43], K-Nearest Neighbor (KNN) method was used to identify poison message failures between components in IP networks. A testbed called OPNET was developed for the simulation of MultiProtocol Label Switching (MPLS) network in which the poison message could be a message in Border Gateway Protocol or Label Distribution Protocol.…”

Section: During 2000smentioning

confidence: 99%

Four Decades of Data Mining in Network and Systems Management

Kalegele

Sasai

Takahashi

et al. 2015

IEEE Trans. Knowl. Data Eng.

View full text Add to dashboard Cite

How has the interdisciplinary data mining field been practiced in Network and Systems Management (NSM)? In Science and Technology, there is a wide use of data mining in areas like bioinformatics, genetics, Web and more recently astroinformatics. However, the application in NSM has been limited and inconsiderable. In this article, we provide an account of how data mining has been applied in managing networks and systems for the past four decades, presumably since its birth. We look into the field's applications in the key NSM activities -discovery, monitoring, analysis, reporting and domain knowledge acquisition. In the end, we discuss our perspective on the issues that are considered critical for the effective application of data mining in the modern systems which are characterized by heterogeneity and high dynamism.

show abstract

“…An improved version to LEACH, LEACH-C [7] uses a centralized clustering algorithm to produce better clusters, thus achieving better performance. TPC [5] (Two-phase Clustering scheme) contains two phases in clustering formation. In the first phase, a direct link between cluster member and cluster head is formed.…”

Section: Cluster-based Network Modelmentioning

confidence: 99%

“…Fault-tolerance is the ability of a network to maintain a desired performance when fault conditions occur. Current fault tolerant research includes self-repair techniques [1][2][3] and the use of existing industry standards such as SNMP and TCP/IP, as well as more integrated techniques that consider energy efficiency [4][5][6]. Ultimately, the problem of designing fault tolerant wireless sensor networks is a research challenge that cannot be addressed in the same way as traditional wired, or even traditional wireless networks due to several unique features.…”

Section: Introductionmentioning

confidence: 99%

Fault-Tolerant Wireless Sensor Networks

Li¹,

McNair²

2009

Security in Ad Hoc and Sensor Networks

View full text Add to dashboard Cite

In this chapter, we outline the current state of research for the design of fault tolerant wireless sensor networks. First, we discuss the various notions of faults as concerns a wireless sensor network, including fault characteristics, sources of faults, and random faults versus faults with particular temporal, geographical, or topology-related patterns. Second, we discuss techniques for fault prevention and management including techniques for detection and recovery. Finally, we provide a particular focus on a fault management in cluster-based wireless sensor networks, and outline current research directions in architecture design and recovery techniques, followed by the chapter summary.

show abstract

Identifying Control and Management Plane Poison Message Failure by K-Nearest Neighbor Method

Cited by 5 publications

References 9 publications

Quantitative Detection of Chromium Pollution in Biochar Based on Matrix Effect Classification Regression Model

Quantitative Detection of Chromium Pollution in Biochar Based on Matrix Effect Classification Regression Model

Four Decades of Data Mining in Network and Systems Management

Fault-Tolerant Wireless Sensor Networks

Contact Info

Product

Resources

About