Developing a pattern discovery method in time series data and its GPU acceleration

Zhu, Huanzhou; Gu, Zhuoer; Zhao, Haiming; Chen, Keyang; Li, Chang-Tsun; He, Ligang

doi:10.26599/bdma.2018.9020021

Cited by 16 publications

(2 citation statements)

References 20 publications

(22 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The Dynamic Time Warping (DTW) loss function is integrated with this network. DTW, a well-known algorithm for measuring the similarity of two time series, is utilized for finding global sequence alignment in various applications, including speech recognition and sepsis prediction tasks [29,30]. The proposed network is empirically validated using real-time data from the HECRAL experimental platform, demonstrating its accuracy and efficacy in beam intensity prediction.…”

Section: Jinst 19 P06028mentioning

confidence: 99%

Ion beam stability prediction of ECR ion source based on TCN-DTW network

Wang,

Qian,

Sun

et al. 2024

J. Inst.

View full text Add to dashboard Cite

The Electron Cyclotron Resonance (ECR) ion source is an irreplaceable apparatus for producing high-intensity, highly charged heavy ion beams, representing a critical component for heavy ion accelerators. The operation of the ECR ion source is inherently influenced by various factors, leading to fluctuations in beam intensity. Such instability not only diminishes the efficacy of accelerator operations but also introduces distortions in terminal experimental data. Addressing these challenges, this study proposes the application of a Temporal Convolutional Network (TCN) based on a Dynamic Time Warping (DTW) loss function (TCN-DTW) for predicting the stability of the ion beams. Prior to constructing the prediction network, raw data undergoes preprocessing through an Interquartile Range (IQR) anomaly detection mechanism and the Savitzky-Golay (SG) filtering algorithm with an adaptive window. Experimental results demonstrate a substantial enhancement in prediction performance when employing the TCN network with the DTW loss function compared to traditional alternatives. This approach facilitates effective forecasting of the ion source beam current trend, offering a basis for the control and correction of long-term stability. Consequently, it provides valuable insights for optimizing the ECR ion source and enhancing overall accelerator operational performance.

show abstract

Section: Jinst 19 P06028mentioning

confidence: 99%

Ion beam stability prediction of ECR ion source based on TCN-DTW network

Wang,

Qian,

Sun

et al. 2024

J. Inst.

View full text Add to dashboard Cite

show abstract

“…b) Loss function: γ-soft-DTW. DTW is widely used in measuring the global similarity of time series [27]. The classic DTW algorithm is based on dynamic programming, which means that it gives a non-linear alignment between two time series.…”

Section: Dcnn Modelmentioning

confidence: 99%

Cross-subject EEG linear domain adaption based on batch normalization and depthwise convolutional neural network

Li,

Ouyang,

Yang

et al. 2023

Knowledge-Based Systems

View full text Add to dashboard Cite

Integrating clustering and regression for workload estimation in the cloud

Yu¹,

Jindal

Yen

et al. 2020

Concurrency and Computation

View full text Add to dashboard Cite

Workload prediction has been widely researched in the literature. However, existing techniques are per-job based and useful for service-like tasks whose workloads exhibit seasonality and trend. But cloud jobs have many different workload patterns and some do not exhibit recurring workload patterns. We consider job-pool-based workload estimation, which analyzes the characteristics of existing tasks' workloads to estimate the currently running tasks' workload. First cluster existing tasks based on their workloads. For a new task J, collect the initial workload of J and determine which cluster J may belong to, then use the cluster's characteristics to estimate J ′ s workload. Based on the Google dataset, the algorithm is experimentally evaluated and its effectiveness is confirmed. However, the workload patterns of some tasks do have seasonality and trend, and conventional per-job-based regression methods may yield better workload prediction results. Also, in some cases, some new tasks may not follow the workload patterns of existing tasks in the pool. Thus, develop an integrated scheme which combines clustering and regression and utilize the best of them for workload prediction. Experimental study shows that the combined approach can further improve the accuracy of workload prediction. K E Y W O R D S cloud computing, dynamic time warp distance, workload clustering, workload estimation 1 INTRODUCTION Cloud computing is very popular covering e-commerce, education, government, and other fields. Studies have shown significant benefits offered by Infrastructure as a Service (IaaS) cloud, including providing a greener computing environment. 1 Many systems are developed to take advantage of the cloud, including big data analytics, offloading from mobile devices 2 and cloud storage systems. 3-5 However, without efficient resource management by the IaaS provider, the potential value of cloud computing cannot be fully realized. One of the important tasks in an IaaS cloud provider is to schedule resource precisely to minimize the cost of the deployment and operation of the cloud platform while fully guarantee the SLA (service level agreement) for each customer. For example, reduction of operating servers by migrating tasks can save power and provide greener computation. In order to manage cloud resources effectively, the future workloads in the cloud should be well predicted. Many workload prediction algorithms are researched in the literature. 6-8 But they use per-job-based methods (which predict a single job's future workload only based on its historical workload) and consider service-like workloads. Generally, services are accessed by users and they run year-round to process user requests. The workload characteristics of a certain systems depend heavily on its user access patterns, and mostly present periodicity and trend. Prediction can be done for these workloads using well-established statistical techniques, such as autocorrelation and regression.

show abstract

Developing a pattern discovery method in time series data and its GPU acceleration

Cited by 16 publications

References 20 publications

Ion beam stability prediction of ECR ion source based on TCN-DTW network

Ion beam stability prediction of ECR ion source based on TCN-DTW network

Cross-subject EEG linear domain adaption based on batch normalization and depthwise convolutional neural network

Integrating clustering and regression for workload estimation in the cloud

Contact Info

Product

Resources

About