Lifelong Disk Failure Prediction via GAN-Based Anomaly Detection

Jiang, Tianming; Zeng, Jiangfeng; Zhou, Ke; Huang, Ping; Yang, Taowei

doi:10.1109/iccd46524.2019.00033

Cited by 20 publications

(7 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…( The S.M.A.R.T. [30] indicators gathered by the sensors installed in the mechanical hard disks for sensoring the mechanical hard disks' status usually have a fault warning characteristic, which are the basis for determining faults [31]. However, there are also some indicators that are not relevant to the failure result-excessive indicators that are useless and may even affect the final analysis result.…”

Section: Algorithmmentioning

confidence: 99%

Convolution-LSTM-Based Mechanical Hard Disk Failure Prediction by Sensoring S.M.A.R.T. Indicators

Shi

Ren

et al. 2022

Journal of Sensors

View full text Add to dashboard Cite

The traditional Infrastructure as a Service (IaaS) cloud platform tends to realize high data availability by introducing dedicated storage devices. However, this heterogeneous architecture has high maintenance cost and might reduce the performance of virtual machines. In homogeneous IaaS cloud platform, servers in the platform would uniformly provide computing resources and storage resources, which effectively solve the above problems, although corresponding mechanisms need to be introduced to improve data availability. Efficient storage resource availability management is one of the key methods to improve data availability. As mechanical hard disk is the main way to realize data storage in IaaS cloud platform at present, timely and accurate prediction of mechanical hard disk failure and active data backup and migration before mechanical hard disk failure would effectively improve the data availability of IaaS cloud platform. In this paper, we propose an improved algorithm for early warning of mechanical hard disk failures. We first use the Relief feature selection algorithm to perform parameter selection. Then, we use the zero-sum game idea of Generative Adversarial Networks (GAN) to generate fewer category samples to achieve a balance of sample data. Finally, an improved Long Short-Term Memory (LSTM) model called Convolution-LSTM (C-LSTM) is used to complete accurate detection of hard disk failures and achieve fault warning. We evaluate several models using precision, recall, and Area Under Curve (AUC) value, and extensive experiments show that our proposed algorithm outperforms other algorithms for mechanical hard disk warning.

show abstract

Section: Algorithmmentioning

confidence: 99%

Convolution-LSTM-Based Mechanical Hard Disk Failure Prediction by Sensoring S.M.A.R.T. Indicators

Shi

Ren

et al. 2022

Journal of Sensors

View full text Add to dashboard Cite

show abstract

“…[131] Various [38], [50]- [52], [62], [67], [71], [79], [96], [107], [111], [120] System Health [16], [28], [53], [57], [58], [92], [100], [116], [125], [139] Image Recognition [25], [47], [51], [55], [63], [66], [86], [88], [89], [95], [136] Manufacturing [33], [40], [44], [69], [77], [99], [108], [124] Autonomous Systems [23], [31], [56], [60], [72], [73], [84], [118] Power/Energy [32], [35], [48], [49],…”

Section: ) Data Augmentation With Generative Adversarial Networkmentioning

confidence: 99%

“…RQ4 showed that only 7% of the primary studies used GANs for anomaly detection in time series data. Therefore, more studies are required on anomaly detection using GANs for time series data to make them suitable for cGAN [26], [37], [39], [56], [57], [64], [65], [72]-[74], [76], [85], [90], [111] Standard GAN [24], [38], [43], [45], [46], [51], [52], [54], [58], [59], [61], [75], [79], [83], [87], [93], [94], [100], [107], [128], [130] Cycle-GAN [48] TextGAN [68] DCGAN [22], [30]- [33], [35], [40], [44], [49], [53], [55], [60], [66], [69], [77], [78], …”

Section: Future Research Directionsmentioning

confidence: 99%

Applications of Generative Adversarial Networks in Anomaly Detection: A Systematic Literature Review

Sabuhi¹,

Zhou

Bezemer

et al. 2021

IEEE Access

View full text Add to dashboard Cite

Anomaly detection has become an indispensable tool for modern society, applied in a wide range of applications, from detecting fraudulent transactions to malignant brain tumors. Over time, many anomaly detection techniques have been introduced. However, in general, they all suffer from the same problem: lack of data that represents anomalous behaviour. As anomalous behaviour is usually costly (or dangerous) for a system, it is difficult to gather enough data that represents such behaviour. This, in turn, makes it difficult to develop and evaluate anomaly detection techniques. Recently, generative adversarial networks (GANs) have attracted much attention in anomaly detection research, due to their unique ability to generate new data. In this paper, we present a systematic review of the literature in this area, covering 128 papers. The goal of this review paper is to analyze the relation between anomaly detection techniques and types of GANs, to identify the most common application domains for GAN-assisted and GAN-based anomaly detection, and to assemble information on datasets and performance metrics used to assess them. Our study helps researchers and practitioners to find the most suitable GAN-assisted anomaly detection technique for their application. In addition, we present a research roadmap for future studies in this area. In summary, GANs are used in anomaly detection to address the problem of insufficient amount of data for the anomalous behaviour, either through data augmentation or representation learning. The most commonly used GAN architectures are DCGANs, standard GANs, and cGANs. The primary application domains include medicine, surveillance and intrusion detection.

show abstract

“…In the era of big data, highly distinguishable feature representation learning has become a new performance bottleneck of AI applications. The past decade has witnessed that deep neural networks including multi-layer nonlinear transformations are able to automatically learn more accurate and effective features from raw data and can be efficiently optimized via layer-wise gradient descent ( Bahdanau, Cho, & Bengio, 2014 ; Jiang, Zeng, Zhou, Huang, & Yang, 2019 ; Shui-Hua & Zhang, 2020 ; Wang, Muhammad, Hong, Sangaiah, & Zhang, 2020 ). Deep learning techniques bring in new insights into fake news detection and have achieved the state-of-the-art performance by automatically extracting features from news textual content ( Chen, Li, Yin, & Zhang, 2018 ; Guo, Cao, Zhang, Guo, & Li, 2018a , 2018b ; Jin, Cao, Zhang, & Luo, 2016 ; Li, Zhang, & Si, 2019 ; Lu & Li, 2020 ).…”

Section: Introductionmentioning

confidence: 99%

Fake news detection for epidemic emergencies via deep correlations between text and images

Zeng

Zhang

2021

Sustainable Cities and Society

View full text Add to dashboard Cite

Lifelong Disk Failure Prediction via GAN-Based Anomaly Detection

Cited by 20 publications

References 20 publications

Convolution-LSTM-Based Mechanical Hard Disk Failure Prediction by Sensoring S.M.A.R.T. Indicators

Convolution-LSTM-Based Mechanical Hard Disk Failure Prediction by Sensoring S.M.A.R.T. Indicators

Applications of Generative Adversarial Networks in Anomaly Detection: A Systematic Literature Review

Fake news detection for epidemic emergencies via deep correlations between text and images

Contact Info

Product

Resources

About