Decentralized Parallel SGD Based on Weight-Balancing for Intelligent IoV

Yuan, Yuan; Yu, Jiguo; Cheng, Xiaolu; Zou, Zongrui; Yu, Dongxiao; Cai, Zhipeng

doi:10.1109/tits.2022.3216709

Cited by 1 publication

(1 citation statement)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Isolation forest [17] is an unsupervised machine learning algorithm, which defines anomalies as points that are widely spaced out from dense populations and have a low density of occurrence. In addition, the idea of other methods based on deep learning [36][37][38][39][40][41] is that if the normal samples are much larger than the anomalous one in the training set, the normal mode of time series will be learned by the reconstruction model or forcasting-based model during the training process. In the detection phase, the data deviating from the learned normal pattern, that is, the reconstruction error or forcasting error greater than the threshold, are defined as anomalies.…”

Section: Related Workmentioning

confidence: 99%

Univariate Time Series Anomaly Detection Based on Hierarchical Attention Network

Chen,

Jia,

Sun

et al. 2024

Tsinghua Sci. Technol.

View full text Add to dashboard Cite

In order to support the perception and defense of the operation risk of the medium and low voltage distribution system, it is crucial to conduct data mining on the time series generated by the system to learn anomalous patterns, and carry out accurate and timely anomaly detection for timely discovery of anomalous conditions and early alerting. And edge computing has been widely used in the processing of Internet of Things (IoT) data. The key challenge of univariate time series anomaly detection is how to model complex nonlinear time dependence. However, most of the previous works only model the short-term time dependence, without considering the periodic long-term time dependence. Therefore, we propose a new Hierarchical Attention Network (HAN), which introduces seven day-level attention networks to capture fine-grained short-term time dependence, and uses a week-level attention network to model the periodic long-term time dependence. Then we combine the day-level feature learned by day-level attention network and week-level feature learned by week-level attention network to obtain the high-level time feature, according to which we can calculate the anomaly probability and further detect the anomaly. Extensive experiments on a public anomaly detection dataset, and deployment in a real-world medium and low voltage distribution system show the superiority of our proposed framework over state-of-the-arts.

show abstract