Anomaly detection(AD)in time series data is widely applied across various industries for monitoring and security applications,emerging as a key research focus within the field of deep learning.While many methods based...Anomaly detection(AD)in time series data is widely applied across various industries for monitoring and security applications,emerging as a key research focus within the field of deep learning.While many methods based on different normality assumptions performwell in specific scenarios,they often neglected the overall normality issue.Some feature extraction methods incorporate pre-training processes but they may not be suitable for time series anomaly detection,leading to decreased performance.Additionally,real-world time series samples are rarely free from noise,making them susceptible to outliers,which further impacts detection accuracy.To address these challenges,we propose a novel anomaly detection method called Robust One-Class Classification Detection(ROC).This approach utilizes an autoencoder(AE)to learn features while constraining the context vectors fromthe AE within a sufficiently small hypersphere,akin to One-Class Classification(OC)methods.By simultaneously optimizing two hypothetical objective functions,ROC captures various aspects of normality.We categorize the input raw time series into clean and outlier sequences,reducing the impact of outliers on compressed feature representation.Experimental results on public datasets indicate that our approach outperforms existing baselinemethods and substantially improves model robustness.展开更多
Time series anomaly detection is crucial in various industrial applications to identify unusual behaviors within the time series data.Due to the challenges associated with annotating anomaly events,time series reconst...Time series anomaly detection is crucial in various industrial applications to identify unusual behaviors within the time series data.Due to the challenges associated with annotating anomaly events,time series reconstruction has become a prevalent approach for unsupervised anomaly detection.However,effectively learning representations and achieving accurate detection results remain challenging due to the intricate temporal patterns and dependencies in real-world time series.In this paper,we propose a cross-dimension attentive feature fusion network for time series anomaly detection,referred to as CAFFN.Specifically,a series and feature mixing block is introduced to learn representations in 1D space.Additionally,a fast Fourier transform is employed to convert the time series into 2D space,providing the capability for 2D feature extraction.Finally,a cross-dimension attentive feature fusion mechanism is designed that adaptively integrates features across different dimensions for anomaly detection.Experimental results on real-world time series datasets demonstrate that CAFFN performs better than other competing methods in time series anomaly detection.展开更多
During the process of preparation and occurrence of a large earthquake, the stress-strain state along the fault zone has close relation with the weak seismicity around the fault zone. The seismic energy release near t...During the process of preparation and occurrence of a large earthquake, the stress-strain state along the fault zone has close relation with the weak seismicity around the fault zone. The seismic energy release near the fault zone before an earthquake can better reflect the dynamic process of earthquake preparation. Thus, in this paper, the method of natural orthogonal function expansion has been adopted to discuss the time variation about the energy field of the seismic activity along the Longmenshan fault zone before the Wenchuan MsS. 0 earthquake, 2008. The results show that evident short-term rise changes appeared in the time factors of the typical field corresponding to several key eigenvalues of the energy field along the Longmenshan fault zone before the Wenchuan earthquake, probably being the short-term anomaly message for this earthquake. Through contrastive analysis of earthquake examples such as the 1976 Tangshan earthquake, the authors think that the study of time variation of energy field of seismicity along active fault zone will be helpful for conducting intentional and intensive earthquake monitoring and forecast in active fault regions with high seismic risk based on medium- and long-term earthquake trend judgment.展开更多
Time-series discord is widely used in data mining applications to characterize anomalous subsequences in time series. Compared to some other discord search algorithms, the direct search algorithm based on the recurren...Time-series discord is widely used in data mining applications to characterize anomalous subsequences in time series. Compared to some other discord search algorithms, the direct search algorithm based on the recurrence plot shows the advantage of being fast and parameter free. The direct search algorithm, however, relies on quasi-periodicity in input time series, an assumption that limits the algorithm＇s applicability. In this paper, we eliminate the periodicity assumption from the direct search algorithm by proposing a reference function for subsequences and a new sampling strategy based on the reference function. These measures result in a new algorithm with improved efficiency and robustness, as evidenced by our empirical evaluation.展开更多
基金supported by the National Natural Science Foundation(62202118)Guizhou Province Major Project(Qiankehe Major Project[2024]014)+3 种基金Science and Scientific and Technological Research Projects from Guizhou Education Department(Qianiao ji[2023]003)Hundred-level Innovative Talent Project of Guizhou Provincial Science and Technology Department(Qiankehe Platform Talent-GCC[2023]018)Guizhou Province Major Project(Qiankehe Major Project[2024]003)Foundation of Chongqing Key Laboratory of Public Big Data Security Technology(CQKL-QJ202300001).
文摘Anomaly detection(AD)in time series data is widely applied across various industries for monitoring and security applications,emerging as a key research focus within the field of deep learning.While many methods based on different normality assumptions performwell in specific scenarios,they often neglected the overall normality issue.Some feature extraction methods incorporate pre-training processes but they may not be suitable for time series anomaly detection,leading to decreased performance.Additionally,real-world time series samples are rarely free from noise,making them susceptible to outliers,which further impacts detection accuracy.To address these challenges,we propose a novel anomaly detection method called Robust One-Class Classification Detection(ROC).This approach utilizes an autoencoder(AE)to learn features while constraining the context vectors fromthe AE within a sufficiently small hypersphere,akin to One-Class Classification(OC)methods.By simultaneously optimizing two hypothetical objective functions,ROC captures various aspects of normality.We categorize the input raw time series into clean and outlier sequences,reducing the impact of outliers on compressed feature representation.Experimental results on public datasets indicate that our approach outperforms existing baselinemethods and substantially improves model robustness.
基金supported in part by the National Natural Science Foundation of China(Grants 62376172,62006163,62376043)in part by the National Postdoctoral Program for Innovative Talents(Grant BX20200226)in part by Sichuan Science and Technology Planning Project(Grants 2022YFSY0047,2022YFQ0014,2023ZYD0143,2022YFH0021,2023YFQ0020,24QYCX0354,24NSFTD0025).
文摘Time series anomaly detection is crucial in various industrial applications to identify unusual behaviors within the time series data.Due to the challenges associated with annotating anomaly events,time series reconstruction has become a prevalent approach for unsupervised anomaly detection.However,effectively learning representations and achieving accurate detection results remain challenging due to the intricate temporal patterns and dependencies in real-world time series.In this paper,we propose a cross-dimension attentive feature fusion network for time series anomaly detection,referred to as CAFFN.Specifically,a series and feature mixing block is introduced to learn representations in 1D space.Additionally,a fast Fourier transform is employed to convert the time series into 2D space,providing the capability for 2D feature extraction.Finally,a cross-dimension attentive feature fusion mechanism is designed that adaptively integrates features across different dimensions for anomaly detection.Experimental results on real-world time series datasets demonstrate that CAFFN performs better than other competing methods in time series anomaly detection.
文摘During the process of preparation and occurrence of a large earthquake, the stress-strain state along the fault zone has close relation with the weak seismicity around the fault zone. The seismic energy release near the fault zone before an earthquake can better reflect the dynamic process of earthquake preparation. Thus, in this paper, the method of natural orthogonal function expansion has been adopted to discuss the time variation about the energy field of the seismic activity along the Longmenshan fault zone before the Wenchuan MsS. 0 earthquake, 2008. The results show that evident short-term rise changes appeared in the time factors of the typical field corresponding to several key eigenvalues of the energy field along the Longmenshan fault zone before the Wenchuan earthquake, probably being the short-term anomaly message for this earthquake. Through contrastive analysis of earthquake examples such as the 1976 Tangshan earthquake, the authors think that the study of time variation of energy field of seismicity along active fault zone will be helpful for conducting intentional and intensive earthquake monitoring and forecast in active fault regions with high seismic risk based on medium- and long-term earthquake trend judgment.
基金Support by Australian Research Council Linkage Grant No. LP 0776417
文摘Time-series discord is widely used in data mining applications to characterize anomalous subsequences in time series. Compared to some other discord search algorithms, the direct search algorithm based on the recurrence plot shows the advantage of being fast and parameter free. The direct search algorithm, however, relies on quasi-periodicity in input time series, an assumption that limits the algorithm＇s applicability. In this paper, we eliminate the periodicity assumption from the direct search algorithm by proposing a reference function for subsequences and a new sampling strategy based on the reference function. These measures result in a new algorithm with improved efficiency and robustness, as evidenced by our empirical evaluation.
