Boxplot Rule - Explore the Science & Experts | ideXlab

Scan Science and Technology

Contact Leading Edge Experts & Companies

Boxplot Rule

The Experts below are selected from a list of 24 Experts worldwide ranked by ideXlab platform

Emmanuel Oyekanlu – 1st expert on this subject based on the ideXlab platform

  • CIC – Osmotic Collaborative Computing for Machine Learning and Cybersecurity Applications in Industrial IoT Networks and Cyber Physical Systems with Gaussian Mixture Models
    2018 IEEE 4th International Conference on Collaboration and Internet Computing (CIC), 2018
    Co-Authors: Emmanuel Oyekanlu

    Abstract:

    To implement machine learning algorithms and other useful algorithms in industrial Internet of Things (IIoT), new computing approaches are needed to prevent costs associated with having to install state of the art edge analytic devices. A suitable approach may include collaborative edge computing using available, resource-constrained IoT edge analytic hardware. In this paper, collaborative computing method is used to construct a popular and very useful waveform for IoT analytics, the Gaussian Mixture Model (GMM). GMM parameters are learned in the cloud, but the GMMs are constructed at the IIoT edge layer. GMMs are constructed using C28x, a ubiquitous, low-cost, embedded digital signal processor (DSP) that is widely available in many pre-existing IIoT infrastructures and in many edge analytic devices. Several GMMs including 2-GMM and 3-GMMs are constructed using the C28x DSP and Embedded C to show that GMM designs could be achieved in form of an osmotic microservice from the IIoT edge to the IIoT fog layer. Designed GMMs are evaluated using their differential and zero-crossings and are found to satisfy important waveform design criteria. At the fog layer, constructed GMMs are then applied for novelty detection, an IIoT cybersecurity and fault-monitoring application and are found to be able to detect anomalies in IIoT machine data using Hampel identifier, 3-Sigma Rule, and the Boxplot Rule. The osmotic collaborative computing method advocated in this paper will be crucial in ensuring the possibility of shifting many complex applications such as novelty detection and other machine learning based cybersecurity applications to edges of large scale IoT networks using low-cost widely available DSPs.

  • Osmotic Collaborative Computing for Machine Learning and Cybersecurity Applications in Industrial IoT Networks and Cyber Physical Systems with Gaussian Mixture Models
    2018 IEEE 4th International Conference on Collaboration and Internet Computing (CIC), 2018
    Co-Authors: Emmanuel Oyekanlu

    Abstract:

    To implement machine learning algorithms and other useful algorithms in industrial Internet of Things (IIoT), new computing approaches are needed to prevent costs associated with having to install state of the art edge analytic devices. A suitable approach may include collaborative edge computing using available, resource-constrained IoT edge analytic hardware. In this paper, collaborative computing method is used to construct a popular and very useful waveform for IoT analytics, the Gaussian Mixture Model (GMM). GMM parameters are learned in the cloud, but the GMMs are constructed at the IIoT edge layer. GMMs are constructed using C28x, a ubiquitous, low-cost, embedded digital signal processor (DSP) that is widely available in many pre-existing IIoT infrastructures and in many edge analytic devices. Several GMMs including 2-GMM and 3-GMMs are constructed using the C28x DSP and Embedded C to show that GMM designs could be achieved in form of an osmotic microservice from the IIoT edge to the IIoT fog layer. Designed GMMs are evaluated using their differential and zero-crossings and are found to satisfy important waveform design criteria. At the fog layer, constructed GMMs are then applied for novelty detection, an IIoT cybersecurity and fault-monitoring application and are found to be able to detect anomalies in IIoT machine data using Hampel identifier, 3-Sigma Rule, and the Boxplot Rule. The osmotic collaborative computing method advocated in this paper will be crucial in ensuring the possibility of shifting many complex applications such as novelty detection and other machine learning based cybersecurity applications to edges of large scale IoT networks using low-cost widely available DSPs.

Jean-françois De Palma – 2nd expert on this subject based on the ideXlab platform

  • Outlier detection Rules for fault detection in solar photovoltaic arrays
    2013 Twenty-Eighth Annual IEEE Applied Power Electronics Conference and Exposition (APEC), 2013
    Co-Authors: Ye Zhao, Brad Lehman, Roy Ball, Jerry Mosesian, Jean-françois De Palma

    Abstract:

    Solar photovoltaic (PV) arrays are unique power sources that may have uncleared fault current when utilizing conventional overcurrent protection devices. To monitor the PV operation and detect these unnoticed faults, outlier detection Rules have been proposed for fault detection based on instantaneous PV string current. This paper discusses three Rules in detail: 3-Sigma Rule, Hampel identifier, and Boxplot Rule. Unlike other methods, the proposed methods do not require weather measurement or efforts in model training. Our experimental results show that Hampel identifier and Boxplot Rule may be recommended for PV fault detection. Furthermore, the proposed models become more reliable as the number of PV measurements increases. The developed methods may be integrated with PV monitoring system for real-time operation.

Abdelrezzak Guessoum – 3rd expert on this subject based on the ideXlab platform

  • fast anomaly detection using Boxplot Rule for multivariate data in cooperative wideband cognitive radio in the presence of jammer
    Security and Communication Networks, 2015
    Co-Authors: Ahmed Moumena, Abdelrezzak Guessoum

    Abstract:

    This work presents a new centralized cooperative compressive spectrum sensing scheme for wideband cognitive radios CRs, which combines intelligent graphical Boxplot Rule detector and compressive sampling technique. The received signal at each CR sensing receiver in the presence of jamming attack signal and adding white Gaussian noise is transformed into a digital signal using an analog-to-information converter via random-demodulator. The proposed approach consists of the anomaly detection using Boxplot Rule technique applied to the compressed measurements obtained from each CR user collected in matrix form called sampling matrix. Cooperation among CR users allows the CR users to detect anomalies or attacks in the presence of noise and jamming attack signal. Furthermore, as an important solution, cooperation makes it possible between all CRs to sample more compressively at every CR, that is, every CR user gives minimum number of samples denoted by Ns. Two hypotheses are proposed in this paper H0 and H1 to know if there is anomalies problem using one of the robust graphical techniques. The results show that the proposed technique performs well in addition to its low complexity. Copyright © 2014 John Wiley & Sons, Ltd.