An irrelevant attributes resistant approach to anomaly detection in high-dimensional space using a deep hypersphere structure

Zheng, Jian; Qu, Hongchun; Li, Zhaoni; Lin, Li; Tang, Xiaoming

doi:10.1016/j.asoc.2021.108301

Cited by 10 publications

(3 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This measure is calculated based on the number of correct anomalies detected samples over the total number of anomaly samples. ARD has been used in evaluating the anomaly detection ratio in studies such as [28].…”

Section: Resultsmentioning

confidence: 99%

A Clustering Algorithm for Evolving Data Streams Using Temporal Spatial Hyper Cube

et al. 2022

View full text Add to dashboard Cite

As applications generate massive amounts of data streams, the requirement for ways to analyze and cluster this data has become a critical field of research for knowledge discovery. Data stream clustering’s primary objective and goal are to acquire insights into incoming data. Recognizing all possible patterns in data streams that enter at variable rates and structures and evolve over time is critical for acquiring insights. Analyzing the data stream has been one of the vital research areas due to the inevitable evolving aspect of the data stream and its vast application domains. Existing algorithms for handling data stream clustering consider adding various data summarization structures starting from grid projection and ending with buffers of Core-Micro and Macro clusters. However, it is found that the static assumption of the data summarization impacts the quality of clustering. To fill this gap, an online clustering algorithm for handling evolving data streams using a tempo-spatial hyper cube called BOCEDS TSHC has been developed in this research. The role of the tempo-spatial hyper cube (TSHC) is to add more dimensions to the data summarization for more degree of freedom. TSHC when added to Buffer-based Online Clustering for Evolving Data Stream (BOCEDS) results in a superior evolving data stream clustering algorithm. Evaluation based on both the real world and synthetic datasets has proven the superiority of the developed BOCEDS TSHC clustering algorithm over the baseline algorithms with respect to most of the clustering metrics.

show abstract

Section: Resultsmentioning

confidence: 99%

A Clustering Algorithm for Evolving Data Streams Using Temporal Spatial Hyper Cube

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Clearly, using autoencoders encodes the input data and then anomalies can be detected in the captured low-dimensional representations ( Zhou et al, 2022 ). Similarly, these examples were implemented in Qu et al (2021) and Zheng et al (2022) .…”

Section: Related Workmentioning

confidence: 99%

Anomaly detection for blueberry data using sparse autoencoder-support vector machine

Dian-wen

Zheng

2023

PeerJ Computer Science

Self Cite

View full text Add to dashboard Cite

High-dimensional space includes many subspaces so that anomalies can be hidden in any of them, which leads to obvious difficulties in abnormality detection. Currently, most existing anomaly detection methods tend to measure distances between data points. Unfortunately, the distance between data points becomes more similar as the dimensionality of the input data increases, resulting in difficulties in differentiation between data points. As such, the high dimensionality of input data brings an obvious challenge for anomaly detection. To address this issue, this article proposes a hybrid method of combining a sparse autoencoder with a support vector machine. The principle is that by first using the proposed sparse autoencoder, the low-dimensional features of the input dataset can be captured, so as to reduce its dimensionality. Then, the support vector machine separates abnormal features from normal features in the captured low-dimensional feature space. To improve the precision of separation, a novel kernel is derived based on the Mercer theorem. Meanwhile, to prevent normal points from being mistakenly classified, the upper limit of the number of abnormal points is estimated by the Chebyshev theorem. Experiments on both the synthetic datasets and the UCI datasets show that the proposed method outperforms the state-of-the-art detection methods in the ability of anomaly detection. We find that the newly designed kernel can explore different sub-regions, which is able to better separate anomaly instances from the normal ones. Moreover, our results suggested that anomaly detection models suffer less negative effects from the complexity of data distribution in the space reconstructed by those layered features than in the original space.

show abstract

“…Firstly, based on the arithmetic optimization algorithm [28], the parameters of the encoder model are optimized, which realizes the adaptive adjustment of the model parameters under different working conditions. Secondly, based on the hypersphere algorithm [29,30], each type of data is trained separately, which alleviates the problem of unbalanced distribution of fault data samples caused by heterogeneities of working conditions. Then, the encoders are combined according to the diagnostic accuracy of the basic models optimized in specific condition, which is helpful to enhance the adaptability in a changing environment.…”

Section: Introductionmentioning

confidence: 99%

Bearing Fault Diagnosis Based on Ensemble Depth Explainable Encoder Classification Model with Arithmetic Optimized Tuning

Zhang¹,

Wang²,

Qu³

2022

J. Engg. Res. & Sci.

Self Cite

View full text Add to dashboard Cite

In a dynamic and complex bearing operating environment, current auto-encoder-based deep models for fault diagnosis are having difficulties in adaptation, which usually leads to a decline in accuracy. Besides, the opaqueness of the decision process by such deep models might reduce the reliability of the diagnostic results, which is not conducive to the subsequent optimization of the model. In this work, an ensemble deep auto-encoder method is developed and tested for intelligent fault diagnosis. To mitigate the influence of the changing operating environment on the diagnostic accuracy of the model, a tuning algorithm is used to adaptively adjust the parameters of the model, and a hypersphere classification algorithm is used to separately train different types of fault data. The encoder components in the ensemble model are automatically updated based on the diagnostic accuracy of the base encoder model under different operating conditions. To improve the reliability of the diagnosis results, the power spectrum analysis and Layer-wise Relevance Propagation algorithm are combined to explain the diagnosis results. The model was validated on three public datasets and compared with individual encoder methods as well as other common fault diagnosis algorithms. The results confirm that the model proposed is flexible enough to cope with changes in operating conditions and has better diagnostic and generalizing capabilities.

show abstract

An irrelevant attributes resistant approach to anomaly detection in high-dimensional space using a deep hypersphere structure

Cited by 10 publications

References 44 publications

A Clustering Algorithm for Evolving Data Streams Using Temporal Spatial Hyper Cube

A Clustering Algorithm for Evolving Data Streams Using Temporal Spatial Hyper Cube

Anomaly detection for blueberry data using sparse autoencoder-support vector machine

Bearing Fault Diagnosis Based on Ensemble Depth Explainable Encoder Classification Model with Arithmetic Optimized Tuning

Contact Info

Product

Resources

About