On the construction of extreme learning machine for online and offline one-class classification—An expanded toolbox

Gautam, Chandan; Tiwari, Aruna; Leng, Qian

doi:10.1016/j.neucom.2016.04.070

Cited by 43 publications

(30 citation statements)

References 52 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For fair comparison, all the test code is implemented by both DDTOOLS [11] and oc-elm toolbox [12] with Matlab under Intel i7 6700, 16GB memory and NVIDIA Geforce 1070. 10-fold cross validation is used to show the runtime and the classification accuracy.…”

Section: Methodsmentioning

confidence: 99%

An Efficient Behavior-based Intrusion Detection System Using OC-ELM for Intelligent Substation in Smart Grid

Fu¹,

Tian²,

Yin³

et al. 2018

dtcse

View full text Add to dashboard Cite

Abstract. Generic Object Oriented Substation Events (GOOSE), as an essential component of IEC 61850 communication standard, plays an important role in intelligent substation. Any abnormal change of GOOSE field values could cause substation automatic system failures, incorrect switching, or physical damages in the field devices, which will result in probably catastrophic losses. To mitigate the risks caused by vulnerabilities of GOOSE protocol, a behavior-based intrusion detection system is proposed. Different from the existing proposed approaches, considering there is no attack traffic in intelligent substation network so far, one class classifier is used to model the normal behaviors. Compared to the existing approaches, it can usually detect much more complex attacks. To specify the proposed system, when giving a GOOSE message, we first convert it into a feature vector with a specific approach. Considering only normal GOOSE messages are given, One Class classifier with Extreme Learning Machine (OC-ELM) is used to model the information embedded in the normal training set. Extensive experiments demonstrate the efficiency and effectiveness of the proposed intrusion detection system.

show abstract

Section: Methodsmentioning

confidence: 99%

An Efficient Behavior-based Intrusion Detection System Using OC-ELM for Intelligent Substation in Smart Grid

Fu¹,

Tian²,

Yin³

et al. 2018

dtcse

View full text Add to dashboard Cite

show abstract

“…Here we have used the OSELM as a one class classifier or anomaly detector in boundary mode [35,36]. That means the network was trained for only one particular class (with only healthy samples from the machine assuming health condition has not degraded at the beginning of the lifetime) and the output of the hidden layer was mapped to only one output node (Y = 1 for healthy samples).…”

Section: Stack Of Artificial Neural Networkmentioning

confidence: 99%

A Stacked Autoencoder Neural Network based Automated Feature Extraction Method for Anomaly detection in On-line Condition Monitoring

Roy

Bose

Kar

et al. 2018

2018 IEEE Symposium Series on Computational Intelligence (SSCI)

View full text Add to dashboard Cite

Condition monitoring is one of the routine tasks in all major process industries. The mechanical parts such as a motor, gear, bearings are the major components of a process industry and any fault in them may cause a total shutdown of the whole process, which may result in serious losses. Therefore, it is very crucial to predict any approaching defects before its occurrence. Several methods exist for this purpose and many research are being carried out for better and efficient models. However, most of them are based on the processing of raw sensor signals, which is tedious and expensive. Recently, there has been an increase in the feature based condition monitoring, where only the useful features are extracted from the raw signals and interpreted for the prediction of the fault. Most of these are handcrafted features, where these are manually obtained based on the nature of the raw data. This of course requires the prior knowledge of the nature of data and related processes. This limits the feature extraction process. However, recent development in the autoencoder based feature extraction method provides an alternative to the traditional handcrafted approaches; however, they have mostly been confined in the area of image and audio processing. In this work, we have developed an automated feature extraction method for on-line condition monitoring based on the stack of the traditional autoencoder and an on-line sequential extreme learning machine(OSELM) network. The performance of this method is comparable to that of the traditional feature extraction approaches. The method can achieve 100% detection accuracy for determining the bearing health states of NASA bearing dataset. The simple design of this method is promising for the easy hardware implementation of Internet of Things(IoT) based prognostics solutions.

show abstract

“…(a) Without Graph-Embedding: KRR-based OCC (KOC) [20] and KRR-based Auto-Encoder model for OCC (AEKOC) [21] (b) With Graph-Embedding: Two types of Graph-Embedding, i.e., Local and Global, have been explored in the literature. Local and Global Graph-Embedding with KOC are named as LKOC-X [22] and GKOC-X [22], LKOC-LLE [22], GKOC-LDA [22], GKOC-CDA [22], GKOC-CV [23] and GKOC-S V [23].…”

Section: Performance Evaluationmentioning

confidence: 99%

“…Codes of all KRR-based one-class classifiers were provided by the authors of the corresponding papers. The implementations of KPCA [14] and AEKOC [21] are obtained from the links given in the paper (links are made available at the reference of the corresponding paper). For all of the kernel-based methods, Radial Basis Function (RBF) kernel is employed as shown below,…”

Section: Performance Evaluationmentioning

confidence: 99%

Minimum Variance-Embedded Multi-layer Kernel Ridge Regression for One-class Classification

Gautam

Tiwari

Iosifidis

2018

2018 IEEE Symposium Series on Computational Intelligence (SSCI)

Self Cite

View full text Add to dashboard Cite

In this paper, a multi-layer architecture (in a hierarchical fashion) by stacking various Kernel Ridge Regression (KRR) based Auto-Encoder for one-class classification is proposed and is referred as MKOC. MKOC has many layers of Auto-Encoders to project the input features into new feature space and the last layer is regression based one class classifier. The Auto-Encoders use an unsupervised approach of learning and the final layer uses semi-supervised (trained by only positive samples) approach of learning. The proposed MKOC is experimentally evaluated on 15 publicly available benchmark datasets. Experimental results verify the effectiveness of the proposed approach over 11 existing state-of-the-art kernel-based one-class classifiers. Friedman test is also performed to verify the statistical significance of the claim of the superiority of the proposed one-class classifiers over the existing state-of-the-art methods. description [5], self-organizing map data description [5], Auto-Encoder data descriptor [11] etc. Whereas, the kernelbased one-class classifier approaches are support vector data description [12], one-class support vector machine[13], kernel principal component analysis based data description [14] etc. However, kernel-based methods have been shown to outperform non-kernel-based methods in the literature [1,5]. Despite this fact, these kernel-based methods involve the solution of a quadratic optimization problem, which is computationally expensive. Apart of these kernel-based methods, KRR-based models [15] optimize the problem rapidly in a non-iterative way by solving a linear systems.Therefore, KRR-based models [15,16,17,18,19] have received quite attention by researchers for solving various types of problems viz., regression, binary, multi-class etc. In recent years, various KRR-based one-class classifiers have been developed and exhibited better performance compared to various state-of-the-art one-class classifiers. Overall, the KRR-based one-class classifiers can be divided into two types, namely, (i) without Graph-Embedding (ii) with Graph-Embedding. For 'without Graph-Embedding', two types of architectures have been explored for OCC. One is KRR-based single output node architecture [20], and other is KRR-based Auto-Encoder architecture [21]. For 'with Graph-Embedding', Iosifidis et al.[22] presented local and global structure. Different types of Laplacian Graphs are employed for local (i.e., Local Linear Embedding, Laplacian Eigenmaps etc.) and global (linear discriminant analysis and clustering-based discriminant analysis etc.) Graph-embedding. Later, global variance-based Graph-Embedding has been extended in order to exploit class variance and sub-class variance information for face verification task by Mygdalis et al.[23]. All the above-mentioned KRR-based one-class classifiers employ a single-layered architectures.Over the last decade, stacked Auto-encoder based multi-layer architectures have received quite attention by researchers for multi-class or binary class classification tasks [24,...

show abstract

On the construction of extreme learning machine for online and offline one-class classification—An expanded toolbox

Cited by 43 publications

References 52 publications

An Efficient Behavior-based Intrusion Detection System Using OC-ELM for Intelligent Substation in Smart Grid

An Efficient Behavior-based Intrusion Detection System Using OC-ELM for Intelligent Substation in Smart Grid

A Stacked Autoencoder Neural Network based Automated Feature Extraction Method for Anomaly detection in On-line Condition Monitoring

Minimum Variance-Embedded Multi-layer Kernel Ridge Regression for One-class Classification

Contact Info

Product

Resources

About